diff --git a/.gitignore b/.gitignore
deleted file mode 100644
index b6e4761..0000000
--- a/.gitignore
+++ /dev/null
@@ -1,129 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-# Usually these files are written by a python script from a template
-# before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-# However, in case of collaboration, if having platform-specific dependencies or dependencies
-# having no cross-platform support, pipenv may install dependencies that don't work, or not
-# install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
diff --git a/06 - Modelo_ALS.ipynb b/06 - Modelo_ALS.ipynb
deleted file mode 100644
index cc9e2f0..0000000
--- a/06 - Modelo_ALS.ipynb
+++ /dev/null
@@ -1,464 +0,0 @@
-{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "colab": {
- "name": "Modelo ALS",
- "provenance": []
- },
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- }
- },
- "cells": [
- {
- "cell_type": "code",
- "metadata": {
- "id": "-CaeYO4F-OPi"
- },
- "source": [
- "# instalar as dependências\n",
- "!apt-get install openjdk-8-jdk-headless -qq > /dev/null\n",
- "!wget -q https://archive.apache.org/dist/spark/spark-2.4.4/spark-2.4.4-bin-hadoop2.7.tgz\n",
- "!tar xf spark-2.4.4-bin-hadoop2.7.tgz\n",
- "!pip install -q findspark"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "sOGzt4aB-fjg"
- },
- "source": [
- "# configurar as variáveis de ambiente\n",
- "import os\n",
- "os.environ[\"JAVA_HOME\"] = \"/usr/lib/jvm/java-8-openjdk-amd64\"\n",
- "os.environ[\"SPARK_HOME\"] = \"/content/spark-2.4.4-bin-hadoop2.7\"\n",
- "\n",
- "# tornar o pyspark \"importável\"\n",
- "import findspark\n",
- "findspark.init('spark-2.4.4-bin-hadoop2.7')"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "uIfWkewv-mXF"
- },
- "source": [
- "from __future__ import print_function\n",
- "\n",
- "import sys\n",
- "if sys.version >= '3':\n",
- " long = int\n",
- "\n",
- "from pyspark.sql import SparkSession\n",
- "\n",
- "from pyspark.ml.evaluation import RegressionEvaluator #evaluation é a biblioteca para verificação da qualidade do modelo\n",
- "from pyspark.ml.recommendation import ALS # ALS é o modelo de recomendação que será utilizadp\n",
- "from pyspark.sql import Row #row é o formato que o ALS trabalha, row conterá o id do usuario, id filme, nota e timestamp"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "o_MjmoGl_AaX"
- },
- "source": [
- "spark = SparkSession.builder.master('local[*]').getOrCreate() #criar/iniciar a sessão spark"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "hbVUD2aqg8Gk"
- },
- "source": [
- "lines = spark.read.text(\"sample_movielens_ratings.txt\").rdd #Carregar os dados. RDD é uma estrutura paralelizada do spark"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "eqqx9-H1_WOX"
- },
- "source": [
- "parts = lines.map(lambda row: row.value.split(\"::\")) #pega os itens de lines e aplica map para quebrar em partes\n",
- "#fez expressão lambda, nomeou cada linha como row e quebra cada row a cada \"::\" retorna um array com 4 itens"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "pWwOX1o4DrlY"
- },
- "source": [
- "#ratingsRDD: pega cada parte do item acima e converte para formato Row, instanciando nome e posição\n",
- "ratingsRDD = parts.map(lambda p: Row(userId=int(p[0]), movieId=int(p[1]), rating=float(p[2]), timestamp=long(p[3])))"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "W5T4NAi1nS2S"
- },
- "source": [
- "ratings = spark.createDataFrame(ratingsRDD) #pega ratingsRDD e coloca em formato de tabela"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "He6QkNy9hXmz",
- "outputId": "993b7a78-0593-43c4-dc99-da1649a8842d"
- },
- "source": [
- "ratings.show()"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "+-------+------+----------+------+\n",
- "|movieId|rating| timestamp|userId|\n",
- "+-------+------+----------+------+\n",
- "| 2| 3.0|1424380312| 0|\n",
- "| 3| 1.0|1424380312| 0|\n",
- "| 5| 2.0|1424380312| 0|\n",
- "| 9| 4.0|1424380312| 0|\n",
- "| 11| 1.0|1424380312| 0|\n",
- "| 12| 2.0|1424380312| 0|\n",
- "| 15| 1.0|1424380312| 0|\n",
- "| 17| 1.0|1424380312| 0|\n",
- "| 19| 1.0|1424380312| 0|\n",
- "| 21| 1.0|1424380312| 0|\n",
- "| 23| 1.0|1424380312| 0|\n",
- "| 26| 3.0|1424380312| 0|\n",
- "| 27| 1.0|1424380312| 0|\n",
- "| 28| 1.0|1424380312| 0|\n",
- "| 29| 1.0|1424380312| 0|\n",
- "| 30| 1.0|1424380312| 0|\n",
- "| 31| 1.0|1424380312| 0|\n",
- "| 34| 1.0|1424380312| 0|\n",
- "| 37| 1.0|1424380312| 0|\n",
- "| 41| 2.0|1424380312| 0|\n",
- "+-------+------+----------+------+\n",
- "only showing top 20 rows\n",
- "\n"
- ],
- "name": "stdout"
- }
- ]
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "-zpPhZ61hgon"
- },
- "source": [
- "(training, test) = ratings.randomSplit([0.8, 0.2]) #divide o df em porções para treinamento e teste"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "jp9FAaBshqUh"
- },
- "source": [
- "als = ALS(maxIter=5, regParam=0.01, userCol=\"userId\", itemCol=\"movieId\", ratingCol=\"rating\", coldStartStrategy=\"drop\")\n",
- "#instancia o modelo ALS; maxIter é o máximo de iterações, regParam é coeficiente de aprendizado,\n",
- "#coldstart é quando o usuário fez poucas iterações com o sistemas ou o sistema tem a matriz muito esparsa, drop: se algum usuário\n",
- "#tiver problema de coldstart, não será considerado no sistema"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "jLt3j9WXhih9"
- },
- "source": [
- "model = als.fit(training) #treina o modelo com o dataset de treinamento"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "ooGOA8s8iLES",
- "outputId": "958ee0da-8f26-4e4a-cc65-e04adf4ee1b4"
- },
- "source": [
- "predictions = model.transform(test) #aplica o modelo no conjunto de teste para fazer predições\n",
- "evaluator = RegressionEvaluator(metricName=\"rmse\", labelCol=\"rating\",\n",
- " predictionCol=\"prediction\")\n",
- "rmse = evaluator.evaluate(predictions)\n",
- "print(\"Erro médio quadrático = \" + str(rmse))"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "Erro médio quadrático = 1.82015383545805\n"
- ],
- "name": "stdout"
- }
- ]
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "1AayAItWmX53"
- },
- "source": [
- "userRec = model.recommendForAllUsers(10) #pegar todos os usuários e gerar 10 recomendações"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "J2D3AX47mbno",
- "outputId": "3d399616-f62d-4435-e038-532c6ec5061a"
- },
- "source": [
- "userRec.show()"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "+------+--------------------+\n",
- "|userId| recommendations|\n",
- "+------+--------------------+\n",
- "| 28|[[91, 7.199192], ...|\n",
- "| 26|[[30, 6.8022966],...|\n",
- "| 27|[[18, 4.345591], ...|\n",
- "| 12|[[35, 5.1877465],...|\n",
- "| 22|[[4, 5.187028], [...|\n",
- "| 1|[[17, 4.4631], [9...|\n",
- "| 13|[[2, 3.0728006], ...|\n",
- "| 6|[[25, 4.814437], ...|\n",
- "| 16|[[76, 5.6596413],...|\n",
- "| 3|[[32, 5.3414116],...|\n",
- "| 20|[[46, 5.877379], ...|\n",
- "| 5|[[18, 4.877655], ...|\n",
- "| 19|[[51, 5.3770857],...|\n",
- "| 15|[[46, 4.7499933],...|\n",
- "| 17|[[90, 5.0351977],...|\n",
- "| 9|[[51, 5.090912], ...|\n",
- "| 4|[[92, 5.3576517],...|\n",
- "| 8|[[25, 5.7912273],...|\n",
- "| 23|[[46, 6.087576], ...|\n",
- "| 7|[[25, 4.92321], [...|\n",
- "+------+--------------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ],
- "name": "stdout"
- }
- ]
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "at1apd0lmhBk"
- },
- "source": [
- "movieRecs = model.recommendForAllItems(10) #faz a transposta da matriz de ratings, a fim de recomendar usuários em potencial para itens específicos"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Al3u35R2mi_p",
- "outputId": "37ff86e2-aff0-4436-fb6f-bdf585502ba0"
- },
- "source": [
- "movieRecs.show()"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "+-------+--------------------+\n",
- "|movieId| recommendations|\n",
- "+-------+--------------------+\n",
- "| 31|[[28, 4.4335637],...|\n",
- "| 85|[[16, 4.4600816],...|\n",
- "| 65|[[23, 4.8359885],...|\n",
- "| 53|[[21, 4.8665752],...|\n",
- "| 78|[[5, 1.405179], [...|\n",
- "| 34|[[23, 5.4059834],...|\n",
- "| 81|[[12, 5.1232557],...|\n",
- "| 28|[[18, 5.062015], ...|\n",
- "| 76|[[16, 5.6596413],...|\n",
- "| 26|[[22, 4.0410576],...|\n",
- "| 27|[[2, 5.0788355], ...|\n",
- "| 44|[[11, 3.253865], ...|\n",
- "| 12|[[28, 4.8772264],...|\n",
- "| 91|[[28, 7.199192], ...|\n",
- "| 22|[[26, 5.148896], ...|\n",
- "| 93|[[27, 1.0710598],...|\n",
- "| 47|[[8, 4.567012], [...|\n",
- "| 1|[[16, 4.053723], ...|\n",
- "| 52|[[8, 4.92321], [2...|\n",
- "| 13|[[23, 4.0366826],...|\n",
- "+-------+--------------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ],
- "name": "stdout"
- }
- ]
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "otO0JDGRmmPd"
- },
- "source": [
- "users = ratings.select(als.getUserCol()).distinct() #selecina os usuários que existem nesse universo"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "tM8z5hpumo-f",
- "outputId": "bbcf1956-9af1-40ac-8f49-41308e775cb1"
- },
- "source": [
- "users.show()"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "+------+\n",
- "|userId|\n",
- "+------+\n",
- "| 26|\n",
- "| 29|\n",
- "| 19|\n",
- "| 0|\n",
- "| 22|\n",
- "| 7|\n",
- "| 25|\n",
- "| 6|\n",
- "| 9|\n",
- "| 27|\n",
- "| 17|\n",
- "| 28|\n",
- "| 5|\n",
- "| 1|\n",
- "| 10|\n",
- "| 3|\n",
- "| 12|\n",
- "| 8|\n",
- "| 11|\n",
- "| 2|\n",
- "+------+\n",
- "only showing top 20 rows\n",
- "\n"
- ],
- "name": "stdout"
- }
- ]
- },
- {
- "cell_type": "code",
- "metadata": {
- "id": "YeIDF41BmtFd"
- },
- "source": [
- "UserRecsOnlyItemId = userRec.select(userRec['userId'], userRec['recommendations']['movieid'])"
- ],
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "JFt5sr2voUbS",
- "outputId": "d056b74c-d451-470f-f39a-1f6d06fd86f8"
- },
- "source": [
- "UserRecsOnlyItemId.show(10, False) #mostra somente as recomendações por usuário"
- ],
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "text": [
- "+------+----------------------------------------+\n",
- "|userId|recommendations.movieid |\n",
- "+------+----------------------------------------+\n",
- "|28 |[91, 92, 12, 81, 79, 31, 89, 49, 35, 82]|\n",
- "|26 |[30, 32, 94, 17, 22, 88, 7, 98, 90, 24] |\n",
- "|27 |[18, 2, 48, 19, 55, 66, 23, 44, 7, 33] |\n",
- "|12 |[35, 81, 17, 88, 79, 64, 69, 27, 31, 16]|\n",
- "|22 |[4, 51, 75, 74, 52, 88, 30, 9, 85, 58] |\n",
- "|1 |[17, 90, 62, 51, 69, 85, 28, 22, 38, 76]|\n",
- "|13 |[2, 52, 29, 18, 53, 9, 43, 92, 58, 83] |\n",
- "|6 |[25, 62, 51, 90, 76, 85, 58, 2, 95, 63] |\n",
- "|16 |[76, 62, 90, 29, 51, 54, 85, 1, 53, 69] |\n",
- "|3 |[32, 51, 30, 80, 7, 85, 76, 8, 29, 87] |\n",
- "+------+----------------------------------------+\n",
- "only showing top 10 rows\n",
- "\n"
- ],
- "name": "stdout"
- }
- ]
- }
- ]
-}
\ No newline at end of file
diff --git a/06- sample_movielens_ratings.txt b/06- sample_movielens_ratings.txt
deleted file mode 100644
index 0889142..0000000
--- a/06- sample_movielens_ratings.txt
+++ /dev/null
@@ -1,1501 +0,0 @@
-0::2::3::1424380312
-0::3::1::1424380312
-0::5::2::1424380312
-0::9::4::1424380312
-0::11::1::1424380312
-0::12::2::1424380312
-0::15::1::1424380312
-0::17::1::1424380312
-0::19::1::1424380312
-0::21::1::1424380312
-0::23::1::1424380312
-0::26::3::1424380312
-0::27::1::1424380312
-0::28::1::1424380312
-0::29::1::1424380312
-0::30::1::1424380312
-0::31::1::1424380312
-0::34::1::1424380312
-0::37::1::1424380312
-0::41::2::1424380312
-0::44::1::1424380312
-0::45::2::1424380312
-0::46::1::1424380312
-0::47::1::1424380312
-0::48::1::1424380312
-0::50::1::1424380312
-0::51::1::1424380312
-0::54::1::1424380312
-0::55::1::1424380312
-0::59::2::1424380312
-0::61::2::1424380312
-0::64::1::1424380312
-0::67::1::1424380312
-0::68::1::1424380312
-0::69::1::1424380312
-0::71::1::1424380312
-0::72::1::1424380312
-0::77::2::1424380312
-0::79::1::1424380312
-0::83::1::1424380312
-0::87::1::1424380312
-0::89::2::1424380312
-0::91::3::1424380312
-0::92::4::1424380312
-0::94::1::1424380312
-0::95::2::1424380312
-0::96::1::1424380312
-0::98::1::1424380312
-0::99::1::1424380312
-1::2::2::1424380312
-1::3::1::1424380312
-1::4::2::1424380312
-1::6::1::1424380312
-1::9::3::1424380312
-1::12::1::1424380312
-1::13::1::1424380312
-1::14::1::1424380312
-1::16::1::1424380312
-1::19::1::1424380312
-1::21::3::1424380312
-1::27::1::1424380312
-1::28::3::1424380312
-1::33::1::1424380312
-1::36::2::1424380312
-1::37::1::1424380312
-1::40::1::1424380312
-1::41::2::1424380312
-1::43::1::1424380312
-1::44::1::1424380312
-1::47::1::1424380312
-1::50::1::1424380312
-1::54::1::1424380312
-1::56::2::1424380312
-1::57::1::1424380312
-1::58::1::1424380312
-1::60::1::1424380312
-1::62::4::1424380312
-1::63::1::1424380312
-1::67::1::1424380312
-1::68::4::1424380312
-1::70::2::1424380312
-1::72::1::1424380312
-1::73::1::1424380312
-1::74::2::1424380312
-1::76::1::1424380312
-1::77::3::1424380312
-1::78::1::1424380312
-1::81::1::1424380312
-1::82::1::1424380312
-1::85::3::1424380312
-1::86::2::1424380312
-1::88::2::1424380312
-1::91::1::1424380312
-1::92::2::1424380312
-1::93::1::1424380312
-1::94::2::1424380312
-1::96::1::1424380312
-1::97::1::1424380312
-2::4::3::1424380312
-2::6::1::1424380312
-2::8::5::1424380312
-2::9::1::1424380312
-2::10::1::1424380312
-2::12::3::1424380312
-2::13::1::1424380312
-2::15::2::1424380312
-2::18::2::1424380312
-2::19::4::1424380312
-2::22::1::1424380312
-2::26::1::1424380312
-2::28::1::1424380312
-2::34::4::1424380312
-2::35::1::1424380312
-2::37::5::1424380312
-2::38::1::1424380312
-2::39::5::1424380312
-2::40::4::1424380312
-2::47::1::1424380312
-2::50::1::1424380312
-2::52::2::1424380312
-2::54::1::1424380312
-2::55::1::1424380312
-2::57::2::1424380312
-2::58::2::1424380312
-2::59::1::1424380312
-2::61::1::1424380312
-2::62::1::1424380312
-2::64::1::1424380312
-2::65::1::1424380312
-2::66::3::1424380312
-2::68::1::1424380312
-2::71::3::1424380312
-2::76::1::1424380312
-2::77::1::1424380312
-2::78::1::1424380312
-2::80::1::1424380312
-2::83::5::1424380312
-2::85::1::1424380312
-2::87::2::1424380312
-2::88::1::1424380312
-2::89::4::1424380312
-2::90::1::1424380312
-2::92::4::1424380312
-2::93::5::1424380312
-3::0::1::1424380312
-3::1::1::1424380312
-3::2::1::1424380312
-3::7::3::1424380312
-3::8::3::1424380312
-3::9::1::1424380312
-3::14::1::1424380312
-3::15::1::1424380312
-3::16::1::1424380312
-3::18::4::1424380312
-3::19::1::1424380312
-3::24::3::1424380312
-3::26::1::1424380312
-3::29::3::1424380312
-3::33::1::1424380312
-3::34::3::1424380312
-3::35::1::1424380312
-3::36::3::1424380312
-3::37::1::1424380312
-3::38::2::1424380312
-3::43::1::1424380312
-3::44::1::1424380312
-3::46::1::1424380312
-3::47::1::1424380312
-3::51::5::1424380312
-3::52::3::1424380312
-3::56::1::1424380312
-3::58::1::1424380312
-3::60::3::1424380312
-3::62::1::1424380312
-3::65::2::1424380312
-3::66::1::1424380312
-3::67::1::1424380312
-3::68::2::1424380312
-3::70::1::1424380312
-3::72::2::1424380312
-3::76::3::1424380312
-3::79::3::1424380312
-3::80::4::1424380312
-3::81::1::1424380312
-3::83::1::1424380312
-3::84::1::1424380312
-3::86::1::1424380312
-3::87::2::1424380312
-3::88::4::1424380312
-3::89::1::1424380312
-3::91::1::1424380312
-3::94::3::1424380312
-4::1::1::1424380312
-4::6::1::1424380312
-4::8::1::1424380312
-4::9::1::1424380312
-4::10::1::1424380312
-4::11::1::1424380312
-4::12::1::1424380312
-4::13::1::1424380312
-4::14::2::1424380312
-4::15::1::1424380312
-4::17::1::1424380312
-4::20::1::1424380312
-4::22::1::1424380312
-4::23::1::1424380312
-4::24::1::1424380312
-4::29::4::1424380312
-4::30::1::1424380312
-4::31::1::1424380312
-4::34::1::1424380312
-4::35::1::1424380312
-4::36::1::1424380312
-4::39::2::1424380312
-4::40::3::1424380312
-4::41::4::1424380312
-4::43::2::1424380312
-4::44::1::1424380312
-4::45::1::1424380312
-4::46::1::1424380312
-4::47::1::1424380312
-4::49::2::1424380312
-4::50::1::1424380312
-4::51::1::1424380312
-4::52::4::1424380312
-4::54::1::1424380312
-4::55::1::1424380312
-4::60::3::1424380312
-4::61::1::1424380312
-4::62::4::1424380312
-4::63::3::1424380312
-4::65::1::1424380312
-4::67::2::1424380312
-4::69::1::1424380312
-4::70::4::1424380312
-4::71::1::1424380312
-4::73::1::1424380312
-4::78::1::1424380312
-4::84::1::1424380312
-4::85::1::1424380312
-4::87::3::1424380312
-4::88::3::1424380312
-4::89::2::1424380312
-4::96::1::1424380312
-4::97::1::1424380312
-4::98::1::1424380312
-4::99::1::1424380312
-5::0::1::1424380312
-5::1::1::1424380312
-5::4::1::1424380312
-5::5::1::1424380312
-5::8::1::1424380312
-5::9::3::1424380312
-5::10::2::1424380312
-5::13::3::1424380312
-5::15::1::1424380312
-5::19::1::1424380312
-5::20::3::1424380312
-5::21::2::1424380312
-5::23::3::1424380312
-5::27::1::1424380312
-5::28::1::1424380312
-5::29::1::1424380312
-5::31::1::1424380312
-5::36::3::1424380312
-5::38::2::1424380312
-5::39::1::1424380312
-5::42::1::1424380312
-5::48::3::1424380312
-5::49::4::1424380312
-5::50::3::1424380312
-5::51::1::1424380312
-5::52::1::1424380312
-5::54::1::1424380312
-5::55::5::1424380312
-5::56::3::1424380312
-5::58::1::1424380312
-5::60::1::1424380312
-5::61::1::1424380312
-5::64::3::1424380312
-5::65::2::1424380312
-5::68::4::1424380312
-5::70::1::1424380312
-5::71::1::1424380312
-5::72::1::1424380312
-5::74::1::1424380312
-5::79::1::1424380312
-5::81::2::1424380312
-5::84::1::1424380312
-5::85::1::1424380312
-5::86::1::1424380312
-5::88::1::1424380312
-5::90::4::1424380312
-5::91::2::1424380312
-5::95::2::1424380312
-5::99::1::1424380312
-6::0::1::1424380312
-6::1::1::1424380312
-6::2::3::1424380312
-6::5::1::1424380312
-6::6::1::1424380312
-6::9::1::1424380312
-6::10::1::1424380312
-6::15::2::1424380312
-6::16::2::1424380312
-6::17::1::1424380312
-6::18::1::1424380312
-6::20::1::1424380312
-6::21::1::1424380312
-6::22::1::1424380312
-6::24::1::1424380312
-6::25::5::1424380312
-6::26::1::1424380312
-6::28::1::1424380312
-6::30::1::1424380312
-6::33::1::1424380312
-6::38::1::1424380312
-6::39::1::1424380312
-6::43::4::1424380312
-6::44::1::1424380312
-6::45::1::1424380312
-6::48::1::1424380312
-6::49::1::1424380312
-6::50::1::1424380312
-6::53::1::1424380312
-6::54::1::1424380312
-6::55::1::1424380312
-6::56::1::1424380312
-6::58::4::1424380312
-6::59::1::1424380312
-6::60::1::1424380312
-6::61::3::1424380312
-6::63::3::1424380312
-6::66::1::1424380312
-6::67::3::1424380312
-6::68::1::1424380312
-6::69::1::1424380312
-6::71::2::1424380312
-6::73::1::1424380312
-6::75::1::1424380312
-6::77::1::1424380312
-6::79::1::1424380312
-6::81::1::1424380312
-6::84::1::1424380312
-6::85::3::1424380312
-6::86::1::1424380312
-6::87::1::1424380312
-6::88::1::1424380312
-6::89::1::1424380312
-6::91::2::1424380312
-6::94::1::1424380312
-6::95::2::1424380312
-6::96::1::1424380312
-7::1::1::1424380312
-7::2::2::1424380312
-7::3::1::1424380312
-7::4::1::1424380312
-7::7::1::1424380312
-7::10::1::1424380312
-7::11::2::1424380312
-7::14::2::1424380312
-7::15::1::1424380312
-7::16::1::1424380312
-7::18::1::1424380312
-7::21::1::1424380312
-7::22::1::1424380312
-7::23::1::1424380312
-7::25::5::1424380312
-7::26::1::1424380312
-7::29::4::1424380312
-7::30::1::1424380312
-7::31::3::1424380312
-7::32::1::1424380312
-7::33::1::1424380312
-7::35::1::1424380312
-7::37::2::1424380312
-7::39::3::1424380312
-7::40::2::1424380312
-7::42::2::1424380312
-7::44::1::1424380312
-7::45::2::1424380312
-7::47::4::1424380312
-7::48::1::1424380312
-7::49::1::1424380312
-7::53::1::1424380312
-7::54::1::1424380312
-7::55::1::1424380312
-7::56::1::1424380312
-7::59::1::1424380312
-7::61::2::1424380312
-7::62::3::1424380312
-7::63::2::1424380312
-7::66::1::1424380312
-7::67::3::1424380312
-7::74::1::1424380312
-7::75::1::1424380312
-7::76::3::1424380312
-7::77::1::1424380312
-7::81::1::1424380312
-7::82::1::1424380312
-7::84::2::1424380312
-7::85::4::1424380312
-7::86::1::1424380312
-7::92::2::1424380312
-7::96::1::1424380312
-7::97::1::1424380312
-7::98::1::1424380312
-8::0::1::1424380312
-8::2::4::1424380312
-8::3::2::1424380312
-8::4::2::1424380312
-8::5::1::1424380312
-8::7::1::1424380312
-8::9::1::1424380312
-8::11::1::1424380312
-8::15::1::1424380312
-8::18::1::1424380312
-8::19::1::1424380312
-8::21::1::1424380312
-8::29::5::1424380312
-8::31::3::1424380312
-8::33::1::1424380312
-8::35::1::1424380312
-8::36::1::1424380312
-8::40::2::1424380312
-8::44::1::1424380312
-8::45::1::1424380312
-8::50::1::1424380312
-8::51::1::1424380312
-8::52::5::1424380312
-8::53::5::1424380312
-8::54::1::1424380312
-8::55::1::1424380312
-8::56::1::1424380312
-8::58::4::1424380312
-8::60::3::1424380312
-8::62::4::1424380312
-8::64::1::1424380312
-8::67::3::1424380312
-8::69::1::1424380312
-8::71::1::1424380312
-8::72::3::1424380312
-8::77::3::1424380312
-8::78::1::1424380312
-8::79::1::1424380312
-8::83::1::1424380312
-8::85::5::1424380312
-8::86::1::1424380312
-8::88::1::1424380312
-8::90::1::1424380312
-8::92::2::1424380312
-8::95::4::1424380312
-8::96::3::1424380312
-8::97::1::1424380312
-8::98::1::1424380312
-8::99::1::1424380312
-9::2::3::1424380312
-9::3::1::1424380312
-9::4::1::1424380312
-9::5::1::1424380312
-9::6::1::1424380312
-9::7::5::1424380312
-9::9::1::1424380312
-9::12::1::1424380312
-9::14::3::1424380312
-9::15::1::1424380312
-9::19::1::1424380312
-9::21::1::1424380312
-9::22::1::1424380312
-9::24::1::1424380312
-9::25::1::1424380312
-9::26::1::1424380312
-9::30::3::1424380312
-9::32::4::1424380312
-9::35::2::1424380312
-9::36::2::1424380312
-9::37::2::1424380312
-9::38::1::1424380312
-9::39::1::1424380312
-9::43::3::1424380312
-9::49::5::1424380312
-9::50::3::1424380312
-9::53::1::1424380312
-9::54::1::1424380312
-9::58::1::1424380312
-9::59::1::1424380312
-9::60::1::1424380312
-9::61::1::1424380312
-9::63::3::1424380312
-9::64::3::1424380312
-9::68::1::1424380312
-9::69::1::1424380312
-9::70::3::1424380312
-9::71::1::1424380312
-9::73::2::1424380312
-9::75::1::1424380312
-9::77::2::1424380312
-9::81::2::1424380312
-9::82::1::1424380312
-9::83::1::1424380312
-9::84::1::1424380312
-9::86::1::1424380312
-9::87::4::1424380312
-9::88::1::1424380312
-9::90::3::1424380312
-9::94::2::1424380312
-9::95::3::1424380312
-9::97::2::1424380312
-9::98::1::1424380312
-10::0::3::1424380312
-10::2::4::1424380312
-10::4::3::1424380312
-10::7::1::1424380312
-10::8::1::1424380312
-10::10::1::1424380312
-10::13::2::1424380312
-10::14::1::1424380312
-10::16::2::1424380312
-10::17::1::1424380312
-10::18::1::1424380312
-10::21::1::1424380312
-10::22::1::1424380312
-10::24::1::1424380312
-10::25::3::1424380312
-10::28::1::1424380312
-10::35::1::1424380312
-10::36::1::1424380312
-10::37::1::1424380312
-10::38::1::1424380312
-10::39::1::1424380312
-10::40::4::1424380312
-10::41::2::1424380312
-10::42::3::1424380312
-10::43::1::1424380312
-10::49::3::1424380312
-10::50::1::1424380312
-10::51::1::1424380312
-10::52::1::1424380312
-10::55::2::1424380312
-10::56::1::1424380312
-10::58::1::1424380312
-10::63::1::1424380312
-10::66::1::1424380312
-10::67::2::1424380312
-10::68::1::1424380312
-10::75::1::1424380312
-10::77::1::1424380312
-10::79::1::1424380312
-10::86::1::1424380312
-10::89::3::1424380312
-10::90::1::1424380312
-10::97::1::1424380312
-10::98::1::1424380312
-11::0::1::1424380312
-11::6::2::1424380312
-11::9::1::1424380312
-11::10::1::1424380312
-11::11::1::1424380312
-11::12::1::1424380312
-11::13::4::1424380312
-11::16::1::1424380312
-11::18::5::1424380312
-11::19::4::1424380312
-11::20::1::1424380312
-11::21::1::1424380312
-11::22::1::1424380312
-11::23::5::1424380312
-11::25::1::1424380312
-11::27::5::1424380312
-11::30::5::1424380312
-11::32::5::1424380312
-11::35::3::1424380312
-11::36::2::1424380312
-11::37::2::1424380312
-11::38::4::1424380312
-11::39::1::1424380312
-11::40::1::1424380312
-11::41::1::1424380312
-11::43::2::1424380312
-11::45::1::1424380312
-11::47::1::1424380312
-11::48::5::1424380312
-11::50::4::1424380312
-11::51::3::1424380312
-11::59::1::1424380312
-11::61::1::1424380312
-11::62::1::1424380312
-11::64::1::1424380312
-11::66::4::1424380312
-11::67::1::1424380312
-11::69::5::1424380312
-11::70::1::1424380312
-11::71::3::1424380312
-11::72::3::1424380312
-11::75::3::1424380312
-11::76::1::1424380312
-11::77::1::1424380312
-11::78::1::1424380312
-11::79::5::1424380312
-11::80::3::1424380312
-11::81::4::1424380312
-11::82::1::1424380312
-11::86::1::1424380312
-11::88::1::1424380312
-11::89::1::1424380312
-11::90::4::1424380312
-11::94::2::1424380312
-11::97::3::1424380312
-11::99::1::1424380312
-12::2::1::1424380312
-12::4::1::1424380312
-12::6::1::1424380312
-12::7::3::1424380312
-12::8::1::1424380312
-12::14::1::1424380312
-12::15::2::1424380312
-12::16::4::1424380312
-12::17::5::1424380312
-12::18::2::1424380312
-12::21::1::1424380312
-12::22::2::1424380312
-12::23::3::1424380312
-12::24::1::1424380312
-12::25::1::1424380312
-12::27::5::1424380312
-12::30::2::1424380312
-12::31::4::1424380312
-12::35::5::1424380312
-12::38::1::1424380312
-12::41::1::1424380312
-12::44::2::1424380312
-12::45::1::1424380312
-12::50::4::1424380312
-12::51::1::1424380312
-12::52::1::1424380312
-12::53::1::1424380312
-12::54::1::1424380312
-12::56::2::1424380312
-12::57::1::1424380312
-12::60::1::1424380312
-12::63::1::1424380312
-12::64::5::1424380312
-12::66::3::1424380312
-12::67::1::1424380312
-12::70::1::1424380312
-12::72::1::1424380312
-12::74::1::1424380312
-12::75::1::1424380312
-12::77::1::1424380312
-12::78::1::1424380312
-12::79::3::1424380312
-12::82::2::1424380312
-12::83::1::1424380312
-12::84::1::1424380312
-12::85::1::1424380312
-12::86::1::1424380312
-12::87::1::1424380312
-12::88::1::1424380312
-12::91::3::1424380312
-12::92::1::1424380312
-12::94::4::1424380312
-12::95::2::1424380312
-12::96::1::1424380312
-12::98::2::1424380312
-13::0::1::1424380312
-13::3::1::1424380312
-13::4::2::1424380312
-13::5::1::1424380312
-13::6::1::1424380312
-13::12::1::1424380312
-13::14::2::1424380312
-13::15::1::1424380312
-13::17::1::1424380312
-13::18::3::1424380312
-13::20::1::1424380312
-13::21::1::1424380312
-13::22::1::1424380312
-13::26::1::1424380312
-13::27::1::1424380312
-13::29::3::1424380312
-13::31::1::1424380312
-13::33::1::1424380312
-13::40::2::1424380312
-13::43::2::1424380312
-13::44::1::1424380312
-13::45::1::1424380312
-13::49::1::1424380312
-13::51::1::1424380312
-13::52::2::1424380312
-13::53::3::1424380312
-13::54::1::1424380312
-13::62::1::1424380312
-13::63::2::1424380312
-13::64::1::1424380312
-13::68::1::1424380312
-13::71::1::1424380312
-13::72::3::1424380312
-13::73::1::1424380312
-13::74::3::1424380312
-13::77::2::1424380312
-13::78::1::1424380312
-13::79::2::1424380312
-13::83::3::1424380312
-13::85::1::1424380312
-13::86::1::1424380312
-13::87::2::1424380312
-13::88::2::1424380312
-13::90::1::1424380312
-13::93::4::1424380312
-13::94::1::1424380312
-13::98::1::1424380312
-13::99::1::1424380312
-14::1::1::1424380312
-14::3::3::1424380312
-14::4::1::1424380312
-14::5::1::1424380312
-14::6::1::1424380312
-14::7::1::1424380312
-14::9::1::1424380312
-14::10::1::1424380312
-14::11::1::1424380312
-14::12::1::1424380312
-14::13::1::1424380312
-14::14::3::1424380312
-14::15::1::1424380312
-14::16::1::1424380312
-14::17::1::1424380312
-14::20::1::1424380312
-14::21::1::1424380312
-14::24::1::1424380312
-14::25::2::1424380312
-14::27::1::1424380312
-14::28::1::1424380312
-14::29::5::1424380312
-14::31::3::1424380312
-14::34::1::1424380312
-14::36::1::1424380312
-14::37::2::1424380312
-14::39::2::1424380312
-14::40::1::1424380312
-14::44::1::1424380312
-14::45::1::1424380312
-14::47::3::1424380312
-14::48::1::1424380312
-14::49::1::1424380312
-14::51::1::1424380312
-14::52::5::1424380312
-14::53::3::1424380312
-14::54::1::1424380312
-14::55::1::1424380312
-14::56::1::1424380312
-14::62::4::1424380312
-14::63::5::1424380312
-14::67::3::1424380312
-14::68::1::1424380312
-14::69::3::1424380312
-14::71::1::1424380312
-14::72::4::1424380312
-14::73::1::1424380312
-14::76::5::1424380312
-14::79::1::1424380312
-14::82::1::1424380312
-14::83::1::1424380312
-14::88::1::1424380312
-14::93::3::1424380312
-14::94::1::1424380312
-14::95::2::1424380312
-14::96::4::1424380312
-14::98::1::1424380312
-15::0::1::1424380312
-15::1::4::1424380312
-15::2::1::1424380312
-15::5::2::1424380312
-15::6::1::1424380312
-15::7::1::1424380312
-15::13::1::1424380312
-15::14::1::1424380312
-15::15::1::1424380312
-15::17::2::1424380312
-15::19::2::1424380312
-15::22::2::1424380312
-15::23::2::1424380312
-15::25::1::1424380312
-15::26::3::1424380312
-15::27::1::1424380312
-15::28::2::1424380312
-15::29::1::1424380312
-15::32::1::1424380312
-15::33::2::1424380312
-15::34::1::1424380312
-15::35::2::1424380312
-15::36::1::1424380312
-15::37::1::1424380312
-15::39::1::1424380312
-15::42::1::1424380312
-15::46::5::1424380312
-15::48::2::1424380312
-15::50::2::1424380312
-15::51::1::1424380312
-15::52::1::1424380312
-15::58::1::1424380312
-15::62::1::1424380312
-15::64::3::1424380312
-15::65::2::1424380312
-15::72::1::1424380312
-15::73::1::1424380312
-15::74::1::1424380312
-15::79::1::1424380312
-15::80::1::1424380312
-15::81::1::1424380312
-15::82::2::1424380312
-15::85::1::1424380312
-15::87::1::1424380312
-15::91::2::1424380312
-15::96::1::1424380312
-15::97::1::1424380312
-15::98::3::1424380312
-16::2::1::1424380312
-16::5::3::1424380312
-16::6::2::1424380312
-16::7::1::1424380312
-16::9::1::1424380312
-16::12::1::1424380312
-16::14::1::1424380312
-16::15::1::1424380312
-16::19::1::1424380312
-16::21::2::1424380312
-16::29::4::1424380312
-16::30::2::1424380312
-16::32::1::1424380312
-16::34::1::1424380312
-16::36::1::1424380312
-16::38::1::1424380312
-16::46::1::1424380312
-16::47::3::1424380312
-16::48::1::1424380312
-16::49::1::1424380312
-16::50::1::1424380312
-16::51::5::1424380312
-16::54::5::1424380312
-16::55::1::1424380312
-16::56::2::1424380312
-16::57::1::1424380312
-16::60::1::1424380312
-16::63::2::1424380312
-16::65::1::1424380312
-16::67::1::1424380312
-16::72::1::1424380312
-16::74::1::1424380312
-16::80::1::1424380312
-16::81::1::1424380312
-16::82::1::1424380312
-16::85::5::1424380312
-16::86::1::1424380312
-16::90::5::1424380312
-16::91::1::1424380312
-16::93::1::1424380312
-16::94::3::1424380312
-16::95::2::1424380312
-16::96::3::1424380312
-16::98::3::1424380312
-16::99::1::1424380312
-17::2::1::1424380312
-17::3::1::1424380312
-17::6::1::1424380312
-17::10::4::1424380312
-17::11::1::1424380312
-17::13::2::1424380312
-17::17::5::1424380312
-17::19::1::1424380312
-17::20::5::1424380312
-17::22::4::1424380312
-17::28::1::1424380312
-17::29::1::1424380312
-17::33::1::1424380312
-17::34::1::1424380312
-17::35::2::1424380312
-17::37::1::1424380312
-17::38::1::1424380312
-17::45::1::1424380312
-17::46::5::1424380312
-17::47::1::1424380312
-17::49::3::1424380312
-17::51::1::1424380312
-17::55::5::1424380312
-17::56::3::1424380312
-17::57::1::1424380312
-17::58::1::1424380312
-17::59::1::1424380312
-17::60::1::1424380312
-17::63::1::1424380312
-17::66::1::1424380312
-17::68::4::1424380312
-17::69::1::1424380312
-17::70::1::1424380312
-17::72::1::1424380312
-17::73::3::1424380312
-17::78::1::1424380312
-17::79::1::1424380312
-17::82::2::1424380312
-17::84::1::1424380312
-17::90::5::1424380312
-17::91::3::1424380312
-17::92::1::1424380312
-17::93::1::1424380312
-17::94::4::1424380312
-17::95::2::1424380312
-17::97::1::1424380312
-18::1::1::1424380312
-18::4::3::1424380312
-18::5::2::1424380312
-18::6::1::1424380312
-18::7::1::1424380312
-18::10::1::1424380312
-18::11::4::1424380312
-18::12::2::1424380312
-18::13::1::1424380312
-18::15::1::1424380312
-18::18::1::1424380312
-18::20::1::1424380312
-18::21::2::1424380312
-18::22::1::1424380312
-18::23::2::1424380312
-18::25::1::1424380312
-18::26::1::1424380312
-18::27::1::1424380312
-18::28::5::1424380312
-18::29::1::1424380312
-18::31::1::1424380312
-18::32::1::1424380312
-18::36::1::1424380312
-18::38::5::1424380312
-18::39::5::1424380312
-18::40::1::1424380312
-18::42::1::1424380312
-18::43::1::1424380312
-18::44::4::1424380312
-18::46::1::1424380312
-18::47::1::1424380312
-18::48::1::1424380312
-18::51::2::1424380312
-18::55::1::1424380312
-18::56::1::1424380312
-18::57::1::1424380312
-18::62::1::1424380312
-18::63::1::1424380312
-18::66::3::1424380312
-18::67::1::1424380312
-18::70::1::1424380312
-18::75::1::1424380312
-18::76::3::1424380312
-18::77::1::1424380312
-18::80::3::1424380312
-18::81::3::1424380312
-18::82::1::1424380312
-18::83::5::1424380312
-18::84::1::1424380312
-18::97::1::1424380312
-18::98::1::1424380312
-18::99::2::1424380312
-19::0::1::1424380312
-19::1::1::1424380312
-19::2::1::1424380312
-19::4::1::1424380312
-19::6::2::1424380312
-19::11::1::1424380312
-19::12::1::1424380312
-19::14::1::1424380312
-19::23::1::1424380312
-19::26::1::1424380312
-19::31::1::1424380312
-19::32::4::1424380312
-19::33::1::1424380312
-19::34::1::1424380312
-19::37::1::1424380312
-19::38::1::1424380312
-19::41::1::1424380312
-19::43::1::1424380312
-19::45::1::1424380312
-19::48::1::1424380312
-19::49::1::1424380312
-19::50::2::1424380312
-19::53::2::1424380312
-19::54::3::1424380312
-19::55::1::1424380312
-19::56::2::1424380312
-19::58::1::1424380312
-19::61::1::1424380312
-19::62::1::1424380312
-19::63::1::1424380312
-19::64::1::1424380312
-19::65::1::1424380312
-19::69::2::1424380312
-19::72::1::1424380312
-19::74::3::1424380312
-19::76::1::1424380312
-19::78::1::1424380312
-19::79::1::1424380312
-19::81::1::1424380312
-19::82::1::1424380312
-19::84::1::1424380312
-19::86::1::1424380312
-19::87::2::1424380312
-19::90::4::1424380312
-19::93::1::1424380312
-19::94::4::1424380312
-19::95::2::1424380312
-19::96::1::1424380312
-19::98::4::1424380312
-20::0::1::1424380312
-20::1::1::1424380312
-20::2::2::1424380312
-20::4::2::1424380312
-20::6::1::1424380312
-20::8::1::1424380312
-20::12::1::1424380312
-20::21::2::1424380312
-20::22::5::1424380312
-20::24::2::1424380312
-20::25::1::1424380312
-20::26::1::1424380312
-20::29::2::1424380312
-20::30::2::1424380312
-20::32::2::1424380312
-20::39::1::1424380312
-20::40::1::1424380312
-20::41::2::1424380312
-20::45::2::1424380312
-20::48::1::1424380312
-20::50::1::1424380312
-20::51::3::1424380312
-20::53::3::1424380312
-20::55::1::1424380312
-20::57::2::1424380312
-20::60::1::1424380312
-20::61::1::1424380312
-20::64::1::1424380312
-20::66::1::1424380312
-20::70::2::1424380312
-20::72::1::1424380312
-20::73::2::1424380312
-20::75::4::1424380312
-20::76::1::1424380312
-20::77::4::1424380312
-20::78::1::1424380312
-20::79::1::1424380312
-20::84::2::1424380312
-20::85::2::1424380312
-20::88::3::1424380312
-20::89::1::1424380312
-20::90::3::1424380312
-20::91::1::1424380312
-20::92::2::1424380312
-20::93::1::1424380312
-20::94::4::1424380312
-20::97::1::1424380312
-21::0::1::1424380312
-21::2::4::1424380312
-21::3::1::1424380312
-21::7::2::1424380312
-21::11::1::1424380312
-21::12::1::1424380312
-21::13::1::1424380312
-21::14::3::1424380312
-21::17::1::1424380312
-21::19::1::1424380312
-21::20::1::1424380312
-21::21::1::1424380312
-21::22::1::1424380312
-21::23::1::1424380312
-21::24::1::1424380312
-21::27::1::1424380312
-21::29::5::1424380312
-21::30::2::1424380312
-21::38::1::1424380312
-21::40::2::1424380312
-21::43::3::1424380312
-21::44::1::1424380312
-21::45::1::1424380312
-21::46::1::1424380312
-21::48::1::1424380312
-21::51::1::1424380312
-21::53::5::1424380312
-21::54::1::1424380312
-21::55::1::1424380312
-21::56::1::1424380312
-21::58::3::1424380312
-21::59::3::1424380312
-21::64::1::1424380312
-21::66::1::1424380312
-21::68::1::1424380312
-21::71::1::1424380312
-21::73::1::1424380312
-21::74::4::1424380312
-21::80::1::1424380312
-21::81::1::1424380312
-21::83::1::1424380312
-21::84::1::1424380312
-21::85::3::1424380312
-21::87::4::1424380312
-21::89::2::1424380312
-21::92::2::1424380312
-21::96::3::1424380312
-21::99::1::1424380312
-22::0::1::1424380312
-22::3::2::1424380312
-22::5::2::1424380312
-22::6::2::1424380312
-22::9::1::1424380312
-22::10::1::1424380312
-22::11::1::1424380312
-22::13::1::1424380312
-22::14::1::1424380312
-22::16::1::1424380312
-22::18::3::1424380312
-22::19::1::1424380312
-22::22::5::1424380312
-22::25::1::1424380312
-22::26::1::1424380312
-22::29::3::1424380312
-22::30::5::1424380312
-22::32::4::1424380312
-22::33::1::1424380312
-22::35::1::1424380312
-22::36::3::1424380312
-22::37::1::1424380312
-22::40::1::1424380312
-22::41::3::1424380312
-22::44::1::1424380312
-22::45::2::1424380312
-22::48::1::1424380312
-22::51::5::1424380312
-22::55::1::1424380312
-22::56::2::1424380312
-22::60::3::1424380312
-22::61::1::1424380312
-22::62::4::1424380312
-22::63::1::1424380312
-22::65::1::1424380312
-22::66::1::1424380312
-22::68::4::1424380312
-22::69::4::1424380312
-22::70::3::1424380312
-22::71::1::1424380312
-22::74::5::1424380312
-22::75::5::1424380312
-22::78::1::1424380312
-22::80::3::1424380312
-22::81::1::1424380312
-22::82::1::1424380312
-22::84::1::1424380312
-22::86::1::1424380312
-22::87::3::1424380312
-22::88::5::1424380312
-22::90::2::1424380312
-22::92::3::1424380312
-22::95::2::1424380312
-22::96::2::1424380312
-22::98::4::1424380312
-22::99::1::1424380312
-23::0::1::1424380312
-23::2::1::1424380312
-23::4::1::1424380312
-23::6::2::1424380312
-23::10::4::1424380312
-23::12::1::1424380312
-23::13::4::1424380312
-23::14::1::1424380312
-23::15::1::1424380312
-23::18::4::1424380312
-23::22::2::1424380312
-23::23::4::1424380312
-23::24::1::1424380312
-23::25::1::1424380312
-23::26::1::1424380312
-23::27::5::1424380312
-23::28::1::1424380312
-23::29::1::1424380312
-23::30::4::1424380312
-23::32::5::1424380312
-23::33::2::1424380312
-23::36::3::1424380312
-23::37::1::1424380312
-23::38::1::1424380312
-23::39::1::1424380312
-23::43::1::1424380312
-23::48::5::1424380312
-23::49::5::1424380312
-23::50::4::1424380312
-23::53::1::1424380312
-23::55::5::1424380312
-23::57::1::1424380312
-23::59::1::1424380312
-23::60::1::1424380312
-23::61::1::1424380312
-23::64::4::1424380312
-23::65::5::1424380312
-23::66::2::1424380312
-23::67::1::1424380312
-23::68::3::1424380312
-23::69::1::1424380312
-23::72::1::1424380312
-23::73::3::1424380312
-23::77::1::1424380312
-23::82::2::1424380312
-23::83::1::1424380312
-23::84::1::1424380312
-23::85::1::1424380312
-23::87::3::1424380312
-23::88::1::1424380312
-23::95::2::1424380312
-23::97::1::1424380312
-24::4::1::1424380312
-24::6::3::1424380312
-24::7::1::1424380312
-24::10::2::1424380312
-24::12::1::1424380312
-24::15::1::1424380312
-24::19::1::1424380312
-24::24::1::1424380312
-24::27::3::1424380312
-24::30::5::1424380312
-24::31::1::1424380312
-24::32::3::1424380312
-24::33::1::1424380312
-24::37::1::1424380312
-24::39::1::1424380312
-24::40::1::1424380312
-24::42::1::1424380312
-24::43::3::1424380312
-24::45::2::1424380312
-24::46::1::1424380312
-24::47::1::1424380312
-24::48::1::1424380312
-24::49::1::1424380312
-24::50::1::1424380312
-24::52::5::1424380312
-24::57::1::1424380312
-24::59::4::1424380312
-24::63::4::1424380312
-24::65::1::1424380312
-24::66::1::1424380312
-24::67::1::1424380312
-24::68::3::1424380312
-24::69::5::1424380312
-24::71::1::1424380312
-24::72::4::1424380312
-24::77::4::1424380312
-24::78::1::1424380312
-24::80::1::1424380312
-24::82::1::1424380312
-24::84::1::1424380312
-24::86::1::1424380312
-24::87::1::1424380312
-24::88::2::1424380312
-24::89::1::1424380312
-24::90::5::1424380312
-24::91::1::1424380312
-24::92::1::1424380312
-24::94::2::1424380312
-24::95::1::1424380312
-24::96::5::1424380312
-24::98::1::1424380312
-24::99::1::1424380312
-25::1::3::1424380312
-25::2::1::1424380312
-25::7::1::1424380312
-25::9::1::1424380312
-25::12::3::1424380312
-25::16::3::1424380312
-25::17::1::1424380312
-25::18::1::1424380312
-25::20::1::1424380312
-25::22::1::1424380312
-25::23::1::1424380312
-25::26::2::1424380312
-25::29::1::1424380312
-25::30::1::1424380312
-25::31::2::1424380312
-25::33::4::1424380312
-25::34::3::1424380312
-25::35::2::1424380312
-25::36::1::1424380312
-25::37::1::1424380312
-25::40::1::1424380312
-25::41::1::1424380312
-25::43::1::1424380312
-25::47::4::1424380312
-25::50::1::1424380312
-25::51::1::1424380312
-25::53::1::1424380312
-25::56::1::1424380312
-25::58::2::1424380312
-25::64::2::1424380312
-25::67::2::1424380312
-25::68::1::1424380312
-25::70::1::1424380312
-25::71::4::1424380312
-25::73::1::1424380312
-25::74::1::1424380312
-25::76::1::1424380312
-25::79::1::1424380312
-25::82::1::1424380312
-25::84::2::1424380312
-25::85::1::1424380312
-25::91::3::1424380312
-25::92::1::1424380312
-25::94::1::1424380312
-25::95::1::1424380312
-25::97::2::1424380312
-26::0::1::1424380312
-26::1::1::1424380312
-26::2::1::1424380312
-26::3::1::1424380312
-26::4::4::1424380312
-26::5::2::1424380312
-26::6::3::1424380312
-26::7::5::1424380312
-26::13::3::1424380312
-26::14::1::1424380312
-26::16::1::1424380312
-26::18::3::1424380312
-26::20::1::1424380312
-26::21::3::1424380312
-26::22::5::1424380312
-26::23::5::1424380312
-26::24::5::1424380312
-26::27::1::1424380312
-26::31::1::1424380312
-26::35::1::1424380312
-26::36::4::1424380312
-26::40::1::1424380312
-26::44::1::1424380312
-26::45::2::1424380312
-26::47::1::1424380312
-26::48::1::1424380312
-26::49::3::1424380312
-26::50::2::1424380312
-26::52::1::1424380312
-26::54::4::1424380312
-26::55::1::1424380312
-26::57::3::1424380312
-26::58::1::1424380312
-26::61::1::1424380312
-26::62::2::1424380312
-26::66::1::1424380312
-26::68::4::1424380312
-26::71::1::1424380312
-26::73::4::1424380312
-26::76::1::1424380312
-26::81::3::1424380312
-26::85::1::1424380312
-26::86::3::1424380312
-26::88::5::1424380312
-26::91::1::1424380312
-26::94::5::1424380312
-26::95::1::1424380312
-26::96::1::1424380312
-26::97::1::1424380312
-27::0::1::1424380312
-27::9::1::1424380312
-27::10::1::1424380312
-27::18::4::1424380312
-27::19::3::1424380312
-27::20::1::1424380312
-27::22::2::1424380312
-27::24::2::1424380312
-27::25::1::1424380312
-27::27::3::1424380312
-27::28::1::1424380312
-27::29::1::1424380312
-27::31::1::1424380312
-27::33::3::1424380312
-27::40::1::1424380312
-27::42::1::1424380312
-27::43::1::1424380312
-27::44::3::1424380312
-27::45::1::1424380312
-27::51::3::1424380312
-27::52::1::1424380312
-27::55::3::1424380312
-27::57::1::1424380312
-27::59::1::1424380312
-27::60::1::1424380312
-27::61::1::1424380312
-27::64::1::1424380312
-27::66::3::1424380312
-27::68::1::1424380312
-27::70::1::1424380312
-27::71::2::1424380312
-27::72::1::1424380312
-27::75::3::1424380312
-27::78::1::1424380312
-27::80::3::1424380312
-27::82::1::1424380312
-27::83::3::1424380312
-27::86::1::1424380312
-27::87::2::1424380312
-27::90::1::1424380312
-27::91::1::1424380312
-27::92::1::1424380312
-27::93::1::1424380312
-27::94::2::1424380312
-27::95::1::1424380312
-27::98::1::1424380312
-28::0::3::1424380312
-28::1::1::1424380312
-28::2::4::1424380312
-28::3::1::1424380312
-28::6::1::1424380312
-28::7::1::1424380312
-28::12::5::1424380312
-28::13::2::1424380312
-28::14::1::1424380312
-28::15::1::1424380312
-28::17::1::1424380312
-28::19::3::1424380312
-28::20::1::1424380312
-28::23::3::1424380312
-28::24::3::1424380312
-28::27::1::1424380312
-28::29::1::1424380312
-28::33::1::1424380312
-28::34::1::1424380312
-28::36::1::1424380312
-28::38::2::1424380312
-28::39::2::1424380312
-28::44::1::1424380312
-28::45::1::1424380312
-28::49::4::1424380312
-28::50::1::1424380312
-28::52::1::1424380312
-28::54::1::1424380312
-28::56::1::1424380312
-28::57::3::1424380312
-28::58::1::1424380312
-28::59::1::1424380312
-28::60::1::1424380312
-28::62::3::1424380312
-28::63::1::1424380312
-28::65::1::1424380312
-28::75::1::1424380312
-28::78::1::1424380312
-28::81::5::1424380312
-28::82::4::1424380312
-28::83::1::1424380312
-28::85::1::1424380312
-28::88::2::1424380312
-28::89::4::1424380312
-28::90::1::1424380312
-28::92::5::1424380312
-28::94::1::1424380312
-28::95::2::1424380312
-28::98::1::1424380312
-28::99::1::1424380312
-29::3::1::1424380312
-29::4::1::1424380312
-29::5::1::1424380312
-29::7::2::1424380312
-29::9::1::1424380312
-29::10::3::1424380312
-29::11::1::1424380312
-29::13::3::1424380312
-29::14::1::1424380312
-29::15::1::1424380312
-29::17::3::1424380312
-29::19::3::1424380312
-29::22::3::1424380312
-29::23::4::1424380312
-29::25::1::1424380312
-29::29::1::1424380312
-29::31::1::1424380312
-29::32::4::1424380312
-29::33::2::1424380312
-29::36::2::1424380312
-29::38::3::1424380312
-29::39::1::1424380312
-29::42::1::1424380312
-29::46::5::1424380312
-29::49::3::1424380312
-29::51::2::1424380312
-29::59::1::1424380312
-29::61::1::1424380312
-29::62::1::1424380312
-29::67::1::1424380312
-29::68::3::1424380312
-29::69::1::1424380312
-29::70::1::1424380312
-29::74::1::1424380312
-29::75::1::1424380312
-29::79::2::1424380312
-29::80::1::1424380312
-29::81::2::1424380312
-29::83::1::1424380312
-29::85::1::1424380312
-29::86::1::1424380312
-29::90::4::1424380312
-29::93::1::1424380312
-29::94::4::1424380312
-29::97::1::1424380312
-29::99::1::1424380312
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/1_Ligacao_banco_dados.ipynb b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/1_Ligacao_banco_dados.ipynb
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/1_Ligacao_banco_dados.ipynb
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/1_Ligacao_banco_dados.ipynb
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/PostgreSQL-logo.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/PostgreSQL-logo.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/PostgreSQL-logo.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/PostgreSQL-logo.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/anp.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/anp.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/anp.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/anp.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime2.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime2.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime2.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime2.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime3.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime3.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime3.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/knime3.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/postgre1.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/postgre1.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/postgre1.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/postgre1.png
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/preco_combustivel.jpeg b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/preco_combustivel.jpeg
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/preco_combustivel.jpeg
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/preco_combustivel.jpeg
diff --git a/Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/tabela_base_dados.png b/Analise de Negocios/Aula2 - Ligacao Banco de Dados/tabela_base_dados.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula2 - Ligacao Banco de Dados/tabela_base_dados.png
rename to Analise de Negocios/Aula2 - Ligacao Banco de Dados/tabela_base_dados.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/2_Geracao_Insights.ipynb b/Analise de Negocios/Aula3 - Geracao Insights/2_Geracao_Insights.ipynb
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/2_Geracao_Insights.ipynb
rename to Analise de Negocios/Aula3 - Geracao Insights/2_Geracao_Insights.ipynb
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/PostgreSQL-logo.png b/Analise de Negocios/Aula3 - Geracao Insights/PostgreSQL-logo.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/PostgreSQL-logo.png
rename to Analise de Negocios/Aula3 - Geracao Insights/PostgreSQL-logo.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/anp.png b/Analise de Negocios/Aula3 - Geracao Insights/anp.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/anp.png
rename to Analise de Negocios/Aula3 - Geracao Insights/anp.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime.png b/Analise de Negocios/Aula3 - Geracao Insights/knime.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime.png
rename to Analise de Negocios/Aula3 - Geracao Insights/knime.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime2.png b/Analise de Negocios/Aula3 - Geracao Insights/knime2.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime2.png
rename to Analise de Negocios/Aula3 - Geracao Insights/knime2.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime3.png b/Analise de Negocios/Aula3 - Geracao Insights/knime3.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/knime3.png
rename to Analise de Negocios/Aula3 - Geracao Insights/knime3.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/postgre1.png b/Analise de Negocios/Aula3 - Geracao Insights/postgre1.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/postgre1.png
rename to Analise de Negocios/Aula3 - Geracao Insights/postgre1.png
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/preco_combustivel.jpeg b/Analise de Negocios/Aula3 - Geracao Insights/preco_combustivel.jpeg
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/preco_combustivel.jpeg
rename to Analise de Negocios/Aula3 - Geracao Insights/preco_combustivel.jpeg
diff --git a/Fase 4/Analise de Negocios/Aula3 - Geracao Insights/tabela_base_dados.png b/Analise de Negocios/Aula3 - Geracao Insights/tabela_base_dados.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula3 - Geracao Insights/tabela_base_dados.png
rename to Analise de Negocios/Aula3 - Geracao Insights/tabela_base_dados.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/3_Tecnicas_Visualizacao.ipynb b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/3_Tecnicas_Visualizacao.ipynb
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/3_Tecnicas_Visualizacao.ipynb
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/3_Tecnicas_Visualizacao.ipynb
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/PostgreSQL-logo.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/PostgreSQL-logo.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/PostgreSQL-logo.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/PostgreSQL-logo.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/anp.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/anp.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/anp.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/anp.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime2.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime2.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime2.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime2.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime3.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime3.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime3.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/knime3.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/postgre1.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/postgre1.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/postgre1.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/postgre1.png
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/preco_combustivel.jpeg b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/preco_combustivel.jpeg
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/preco_combustivel.jpeg
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/preco_combustivel.jpeg
diff --git a/Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/tabela_base_dados.png b/Analise de Negocios/Aula4 - Tecnicas Visualizacao/tabela_base_dados.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula4 - Tecnicas Visualizacao/tabela_base_dados.png
rename to Analise de Negocios/Aula4 - Tecnicas Visualizacao/tabela_base_dados.png
diff --git a/Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/analise_negocios_fiap.pbix b/Analise de Negocios/Aula5 - Dashboard Storytelling/analise_negocios_fiap.pbix
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/analise_negocios_fiap.pbix
rename to Analise de Negocios/Aula5 - Dashboard Storytelling/analise_negocios_fiap.pbix
diff --git a/Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel-fossil.png b/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel-fossil.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel-fossil.png
rename to Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel-fossil.png
diff --git a/Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel.png b/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel.png
rename to Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel.png
diff --git a/Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel1.png b/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel1.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel1.png
rename to Analise de Negocios/Aula5 - Dashboard Storytelling/combustivel1.png
diff --git a/Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/filtro-limpo.png b/Analise de Negocios/Aula5 - Dashboard Storytelling/filtro-limpo.png
similarity index 100%
rename from Fase 4/Analise de Negocios/Aula5 - Dashboard Storytelling/filtro-limpo.png
rename to Analise de Negocios/Aula5 - Dashboard Storytelling/filtro-limpo.png
diff --git a/LICENSE b/LICENSE
deleted file mode 100644
index be2367d..0000000
--- a/LICENSE
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2023 FIAP - Faculdade de Informática e Administração Paulista
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
diff --git a/PySpark_Column_Operations.ipynb b/PySpark_Column_Operations.ipynb
deleted file mode 100644
index 18b6cf1..0000000
--- a/PySpark_Column_Operations.ipynb
+++ /dev/null
@@ -1,523 +0,0 @@
-{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "colab": {
- "provenance": [],
- "toc_visible": true
- },
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- },
- "language_info": {
- "name": "python"
- }
- },
- "cells": [
- {
- "cell_type": "markdown",
- "source": [
- "# Creating New Column in PySpark DataFrame"
- ],
- "metadata": {
- "id": "fp0aNsCIYV4Y"
- }
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Installing Libraries"
- ],
- "metadata": {
- "id": "lTIwmVXEYvqO"
- }
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "cDM0Ro4QYPk6",
- "outputId": "f8604fd9-62d7-4028-b878-22b19232e7e9"
- },
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Collecting pyspark\n",
- " Downloading pyspark-3.4.1.tar.gz (310.8 MB)\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.8/310.8 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- "Requirement already satisfied: py4j==0.10.9.7 in /usr/local/lib/python3.10/dist-packages (from pyspark) (0.10.9.7)\n",
- "Building wheels for collected packages: pyspark\n",
- " Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- " Created wheel for pyspark: filename=pyspark-3.4.1-py2.py3-none-any.whl size=311285398 sha256=9d5e11cdda8c083c4d6eb0805f2784034981f8e4973d28bf226c6ddba9174b07\n",
- " Stored in directory: /root/.cache/pip/wheels/0d/77/a3/ff2f74cc9ab41f8f594dabf0579c2a7c6de920d584206e0834\n",
- "Successfully built pyspark\n",
- "Installing collected packages: pyspark\n",
- "Successfully installed pyspark-3.4.1\n"
- ]
- }
- ],
- "source": [
- "!pip install pyspark"
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Importing the Libraries"
- ],
- "metadata": {
- "id": "1TZXyu1vYzEX"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "from pyspark.sql import SparkSession"
- ],
- "metadata": {
- "id": "J2RVV_40Ygnv"
- },
- "execution_count": 2,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Creating Spark Session"
- ],
- "metadata": {
- "id": "3RmGsf2WY42f"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "spark = SparkSession.builder.appName('PySpark Column Ops').getOrCreate()"
- ],
- "metadata": {
- "id": "3gN4uCH6YkY8"
- },
- "execution_count": 3,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Reading the Dataset"
- ],
- "metadata": {
- "id": "1CVP3cmxY6u7"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df = spark.read.csv('Fish.csv', sep = ',', inferSchema = True, header = True)"
- ],
- "metadata": {
- "id": "sqAlMbX1YmpR"
- },
- "execution_count": 5,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Checking the Imported Dataset"
- ],
- "metadata": {
- "id": "06IlRwQwY8uz"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "2t_6cc-NY-KE",
- "outputId": "00bfd217-ef19-493b-c56b-184ae7777c38"
- },
- "execution_count": 6,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+-------+------+-------+-------+-------+-------+------+\n",
- "|Species|Weight|Length1|Length2|Length3| Height| Width|\n",
- "+-------+------+-------+-------+-------+-------+------+\n",
- "| Bream| 242.0| 23.2| 25.4| 30.0| 11.52| 4.02|\n",
- "| Bream| 290.0| 24.0| 26.3| 31.2| 12.48|4.3056|\n",
- "| Bream| 340.0| 23.9| 26.5| 31.1|12.3778|4.6961|\n",
- "| Bream| 363.0| 26.3| 29.0| 33.5| 12.73|4.4555|\n",
- "| Bream| 430.0| 26.5| 29.0| 34.0| 12.444| 5.134|\n",
- "| Bream| 450.0| 26.8| 29.7| 34.7|13.6024|4.9274|\n",
- "| Bream| 500.0| 26.8| 29.7| 34.5|14.1795|5.2785|\n",
- "| Bream| 390.0| 27.6| 30.0| 35.0| 12.67| 4.69|\n",
- "| Bream| 450.0| 27.6| 30.0| 35.1|14.0049|4.8438|\n",
- "| Bream| 500.0| 28.5| 30.7| 36.2|14.2266|4.9594|\n",
- "| Bream| 475.0| 28.4| 31.0| 36.2|14.2628|5.1042|\n",
- "| Bream| 500.0| 28.7| 31.0| 36.2|14.3714|4.8146|\n",
- "| Bream| 500.0| 29.1| 31.5| 36.4|13.7592| 4.368|\n",
- "| Bream| 340.0| 29.5| 32.0| 37.3|13.9129|5.0728|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2|14.9544|5.1708|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2| 15.438| 5.58|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.3|14.8604|5.2854|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.5| 14.938|5.1975|\n",
- "| Bream| 610.0| 30.9| 33.5| 38.6| 15.633|5.1338|\n",
- "| Bream| 650.0| 31.0| 33.5| 38.7|14.4738|5.7276|\n",
- "+-------+------+-------+-------+-------+-------+------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Creating a New Column"
- ],
- "metadata": {
- "id": "fCiQ5-e6Y_uD"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df = df.withColumn('Weight in Kg', df.Weight/1000)"
- ],
- "metadata": {
- "id": "OoRAx0zKZD0r"
- },
- "execution_count": 7,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Checking the Updated DataFrame\n"
- ],
- "metadata": {
- "id": "lhwSPTh-ZHGH"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "1btXaw6vZJfv",
- "outputId": "f0dc6e23-02e0-426c-f165-7eca346d5c95"
- },
- "execution_count": 8,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "|Species|Weight|Length1|Length2|Length3| Height| Width|Weight in Kg|\n",
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "| Bream| 242.0| 23.2| 25.4| 30.0| 11.52| 4.02| 0.242|\n",
- "| Bream| 290.0| 24.0| 26.3| 31.2| 12.48|4.3056| 0.29|\n",
- "| Bream| 340.0| 23.9| 26.5| 31.1|12.3778|4.6961| 0.34|\n",
- "| Bream| 363.0| 26.3| 29.0| 33.5| 12.73|4.4555| 0.363|\n",
- "| Bream| 430.0| 26.5| 29.0| 34.0| 12.444| 5.134| 0.43|\n",
- "| Bream| 450.0| 26.8| 29.7| 34.7|13.6024|4.9274| 0.45|\n",
- "| Bream| 500.0| 26.8| 29.7| 34.5|14.1795|5.2785| 0.5|\n",
- "| Bream| 390.0| 27.6| 30.0| 35.0| 12.67| 4.69| 0.39|\n",
- "| Bream| 450.0| 27.6| 30.0| 35.1|14.0049|4.8438| 0.45|\n",
- "| Bream| 500.0| 28.5| 30.7| 36.2|14.2266|4.9594| 0.5|\n",
- "| Bream| 475.0| 28.4| 31.0| 36.2|14.2628|5.1042| 0.475|\n",
- "| Bream| 500.0| 28.7| 31.0| 36.2|14.3714|4.8146| 0.5|\n",
- "| Bream| 500.0| 29.1| 31.5| 36.4|13.7592| 4.368| 0.5|\n",
- "| Bream| 340.0| 29.5| 32.0| 37.3|13.9129|5.0728| 0.34|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2|14.9544|5.1708| 0.6|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2| 15.438| 5.58| 0.6|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.3|14.8604|5.2854| 0.7|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.5| 14.938|5.1975| 0.7|\n",
- "| Bream| 610.0| 30.9| 33.5| 38.6| 15.633|5.1338| 0.61|\n",
- "| Bream| 650.0| 31.0| 33.5| 38.7|14.4738|5.7276| 0.65|\n",
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Renaming an Existing Column in PySpark DataFrame\n"
- ],
- "metadata": {
- "id": "4N0umJ_BZLz3"
- }
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Checking the Current PySpark DataFrame"
- ],
- "metadata": {
- "id": "vrEzPB7IZORL"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "DqYVlcNUZN7p",
- "outputId": "7103be5a-8881-40c3-e3aa-e3e8e0fe7705"
- },
- "execution_count": 9,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "|Species|Weight|Length1|Length2|Length3| Height| Width|Weight in Kg|\n",
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "| Bream| 242.0| 23.2| 25.4| 30.0| 11.52| 4.02| 0.242|\n",
- "| Bream| 290.0| 24.0| 26.3| 31.2| 12.48|4.3056| 0.29|\n",
- "| Bream| 340.0| 23.9| 26.5| 31.1|12.3778|4.6961| 0.34|\n",
- "| Bream| 363.0| 26.3| 29.0| 33.5| 12.73|4.4555| 0.363|\n",
- "| Bream| 430.0| 26.5| 29.0| 34.0| 12.444| 5.134| 0.43|\n",
- "| Bream| 450.0| 26.8| 29.7| 34.7|13.6024|4.9274| 0.45|\n",
- "| Bream| 500.0| 26.8| 29.7| 34.5|14.1795|5.2785| 0.5|\n",
- "| Bream| 390.0| 27.6| 30.0| 35.0| 12.67| 4.69| 0.39|\n",
- "| Bream| 450.0| 27.6| 30.0| 35.1|14.0049|4.8438| 0.45|\n",
- "| Bream| 500.0| 28.5| 30.7| 36.2|14.2266|4.9594| 0.5|\n",
- "| Bream| 475.0| 28.4| 31.0| 36.2|14.2628|5.1042| 0.475|\n",
- "| Bream| 500.0| 28.7| 31.0| 36.2|14.3714|4.8146| 0.5|\n",
- "| Bream| 500.0| 29.1| 31.5| 36.4|13.7592| 4.368| 0.5|\n",
- "| Bream| 340.0| 29.5| 32.0| 37.3|13.9129|5.0728| 0.34|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2|14.9544|5.1708| 0.6|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2| 15.438| 5.58| 0.6|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.3|14.8604|5.2854| 0.7|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.5| 14.938|5.1975| 0.7|\n",
- "| Bream| 610.0| 30.9| 33.5| 38.6| 15.633|5.1338| 0.61|\n",
- "| Bream| 650.0| 31.0| 33.5| 38.7|14.4738|5.7276| 0.65|\n",
- "+-------+------+-------+-------+-------+-------+------+------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Renaming the Column\n"
- ],
- "metadata": {
- "id": "zjHt7IsIZS1A"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df = df.withColumnRenamed(\"Weight in Kg\", \"Weight in Kilograms\")"
- ],
- "metadata": {
- "id": "vZDmqdEFZWOV"
- },
- "execution_count": 17,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Checking the updated PySpark DataFrame"
- ],
- "metadata": {
- "id": "DIQa3FRBZYGb"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "c_UHQ8XWZiVF",
- "outputId": "b087cb0b-681e-4ac5-91aa-b8e32435c428"
- },
- "execution_count": 11,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "|Species|Weight|Length1|Length2|Length3| Height| Width|Weight in Kilograms|\n",
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "| Bream| 242.0| 23.2| 25.4| 30.0| 11.52| 4.02| 0.242|\n",
- "| Bream| 290.0| 24.0| 26.3| 31.2| 12.48|4.3056| 0.29|\n",
- "| Bream| 340.0| 23.9| 26.5| 31.1|12.3778|4.6961| 0.34|\n",
- "| Bream| 363.0| 26.3| 29.0| 33.5| 12.73|4.4555| 0.363|\n",
- "| Bream| 430.0| 26.5| 29.0| 34.0| 12.444| 5.134| 0.43|\n",
- "| Bream| 450.0| 26.8| 29.7| 34.7|13.6024|4.9274| 0.45|\n",
- "| Bream| 500.0| 26.8| 29.7| 34.5|14.1795|5.2785| 0.5|\n",
- "| Bream| 390.0| 27.6| 30.0| 35.0| 12.67| 4.69| 0.39|\n",
- "| Bream| 450.0| 27.6| 30.0| 35.1|14.0049|4.8438| 0.45|\n",
- "| Bream| 500.0| 28.5| 30.7| 36.2|14.2266|4.9594| 0.5|\n",
- "| Bream| 475.0| 28.4| 31.0| 36.2|14.2628|5.1042| 0.475|\n",
- "| Bream| 500.0| 28.7| 31.0| 36.2|14.3714|4.8146| 0.5|\n",
- "| Bream| 500.0| 29.1| 31.5| 36.4|13.7592| 4.368| 0.5|\n",
- "| Bream| 340.0| 29.5| 32.0| 37.3|13.9129|5.0728| 0.34|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2|14.9544|5.1708| 0.6|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2| 15.438| 5.58| 0.6|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.3|14.8604|5.2854| 0.7|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.5| 14.938|5.1975| 0.7|\n",
- "| Bream| 610.0| 30.9| 33.5| 38.6| 15.633|5.1338| 0.61|\n",
- "| Bream| 650.0| 31.0| 33.5| 38.7|14.4738|5.7276| 0.65|\n",
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Creating a Column Alias in PySpark DataFrame"
- ],
- "metadata": {
- "id": "fs6mwFAUZkrz"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "HGG4KSgNZmnZ",
- "outputId": "c8156606-03a5-47d8-ead6-14fbb9f6db48"
- },
- "execution_count": 12,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "|Species|Weight|Length1|Length2|Length3| Height| Width|Weight in Kilograms|\n",
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "| Bream| 242.0| 23.2| 25.4| 30.0| 11.52| 4.02| 0.242|\n",
- "| Bream| 290.0| 24.0| 26.3| 31.2| 12.48|4.3056| 0.29|\n",
- "| Bream| 340.0| 23.9| 26.5| 31.1|12.3778|4.6961| 0.34|\n",
- "| Bream| 363.0| 26.3| 29.0| 33.5| 12.73|4.4555| 0.363|\n",
- "| Bream| 430.0| 26.5| 29.0| 34.0| 12.444| 5.134| 0.43|\n",
- "| Bream| 450.0| 26.8| 29.7| 34.7|13.6024|4.9274| 0.45|\n",
- "| Bream| 500.0| 26.8| 29.7| 34.5|14.1795|5.2785| 0.5|\n",
- "| Bream| 390.0| 27.6| 30.0| 35.0| 12.67| 4.69| 0.39|\n",
- "| Bream| 450.0| 27.6| 30.0| 35.1|14.0049|4.8438| 0.45|\n",
- "| Bream| 500.0| 28.5| 30.7| 36.2|14.2266|4.9594| 0.5|\n",
- "| Bream| 475.0| 28.4| 31.0| 36.2|14.2628|5.1042| 0.475|\n",
- "| Bream| 500.0| 28.7| 31.0| 36.2|14.3714|4.8146| 0.5|\n",
- "| Bream| 500.0| 29.1| 31.5| 36.4|13.7592| 4.368| 0.5|\n",
- "| Bream| 340.0| 29.5| 32.0| 37.3|13.9129|5.0728| 0.34|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2|14.9544|5.1708| 0.6|\n",
- "| Bream| 600.0| 29.4| 32.0| 37.2| 15.438| 5.58| 0.6|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.3|14.8604|5.2854| 0.7|\n",
- "| Bream| 700.0| 30.4| 33.0| 38.5| 14.938|5.1975| 0.7|\n",
- "| Bream| 610.0| 30.9| 33.5| 38.6| 15.633|5.1338| 0.61|\n",
- "| Bream| 650.0| 31.0| 33.5| 38.7|14.4738|5.7276| 0.65|\n",
- "+-------+------+-------+-------+-------+-------+------+-------------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Creating Column Column Alias\n",
- "\n"
- ],
- "metadata": {
- "id": "HfDsR4q4aAzS"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.select(df['Weight in Kilograms'].alias(\"Kilograms\")).show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "ohVBLfInaC0J",
- "outputId": "e42cbe8c-359f-403e-abed-0e23c793e4d0"
- },
- "execution_count": 16,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+---------+\n",
- "|Kilograms|\n",
- "+---------+\n",
- "| 0.242|\n",
- "| 0.29|\n",
- "| 0.34|\n",
- "| 0.363|\n",
- "| 0.43|\n",
- "| 0.45|\n",
- "| 0.5|\n",
- "| 0.39|\n",
- "| 0.45|\n",
- "| 0.5|\n",
- "| 0.475|\n",
- "| 0.5|\n",
- "| 0.5|\n",
- "| 0.34|\n",
- "| 0.6|\n",
- "| 0.6|\n",
- "| 0.7|\n",
- "| 0.7|\n",
- "| 0.61|\n",
- "| 0.65|\n",
- "+---------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- }
- ]
-}
\ No newline at end of file
diff --git a/PySpark_DataManipulation.ipynb b/PySpark_DataManipulation.ipynb
deleted file mode 100644
index 254a32f..0000000
--- a/PySpark_DataManipulation.ipynb
+++ /dev/null
@@ -1,1032 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "lihDEjAhyqca"
- },
- "source": [
- "# Spark 101 - Data Manipulation using Spark\n",
- "
"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "o9t08dFEeA9W"
- },
- "source": [
- "## **1. Running Spark in Colab**"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "e8dsXbdzzHDc"
- },
- "source": [
- "### 1.1 Initialize Spark"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "anLHk85lyQ5G",
- "outputId": "e1b1f057-ac20-4a87-a1bb-8e910fe3dd22"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Collecting pyspark\n",
- " Downloading pyspark-3.4.1.tar.gz (310.8 MB)\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.8/310.8 MB\u001b[0m \u001b[31m3.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- "Requirement already satisfied: py4j==0.10.9.7 in /usr/local/lib/python3.10/dist-packages (from pyspark) (0.10.9.7)\n",
- "Building wheels for collected packages: pyspark\n",
- " Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- " Created wheel for pyspark: filename=pyspark-3.4.1-py2.py3-none-any.whl size=311285398 sha256=5377e2774d9b2079e8a446797edb3f0cd65734b9f8bdeb07ff2c99f7b9ac184b\n",
- " Stored in directory: /root/.cache/pip/wheels/0d/77/a3/ff2f74cc9ab41f8f594dabf0579c2a7c6de920d584206e0834\n",
- "Successfully built pyspark\n",
- "Installing collected packages: pyspark\n",
- "Successfully installed pyspark-3.4.1\n"
- ]
- }
- ],
- "source": [
- "!pip install pyspark"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "rt3m6PxECGIY",
- "outputId": "698a4c0b-6fc9-4178-fb0b-9df581684e60"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Collecting findspark\n",
- " Downloading findspark-2.0.1-py2.py3-none-any.whl (4.4 kB)\n",
- "Installing collected packages: findspark\n",
- "Successfully installed findspark-2.0.1\n"
- ]
- }
- ],
- "source": [
- "!pip install findspark"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {
- "id": "gJ6HCddh0rBI"
- },
- "outputs": [],
- "source": [
- "import findspark\n",
- "findspark.init()\n",
- "from pyspark.sql import SparkSession\n",
- "spark = SparkSession.builder.master(\"local[*]\").getOrCreate()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "77fvmo9F0szJ",
- "outputId": "abdb4099-e584-451e-f3fc-4cc075531564"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+-----+\n",
- "|hello|\n",
- "+-----+\n",
- "|spark|\n",
- "+-----+\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# Check if spark is initialized\n",
- "df = spark.sql('''select 'Sucesso total, estamos online!' as hello''')\n",
- "df.show()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {
- "id": "QWbHuaova0PH"
- },
- "outputs": [],
- "source": [
- "# Import spark libraries\n",
- "from pyspark.sql import Row, DataFrame\n",
- "from pyspark.sql.types import StringType, StructType, StructField, IntegerType\n",
- "from pyspark.sql.functions import col, expr, lit, substring, concat, concat_ws, when, coalesce\n",
- "from pyspark.sql import functions as F # for more sql functions\n",
- "from functools import reduce"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "tDLaLZjzzpWg"
- },
- "source": [
- "# Data manipulation using spark"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "1Ql57n4Iz4kX",
- "outputId": "ed890508-2f5c-4de4-c1f7-c0f067821804"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "df.count : 561\n",
- "df.col ct : 6\n",
- "df.columns: ['Bank Name', 'City', 'ST', 'CERT', 'Acquiring Institution', 'Closing Date']\n"
- ]
- }
- ],
- "source": [
- "df = spark.read.csv('banklist.csv', sep = ',', inferSchema = True, header = True)\n",
- "\n",
- "print('df.count :', df.count())\n",
- "print('df.col ct :', len(df.columns))\n",
- "print('df.columns:', df.columns)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "lviT9J99TMmr"
- },
- "source": [
- "### **3. Using SQL in spark**"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Jce3V6YyT_tm",
- "outputId": "3b1360dc-bbf9-4584-f501-f66baf608816"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------------------+-------------+------------+\n",
- "|Bank Name |City |Closing Date|\n",
- "+--------------------------------+-------------+------------+\n",
- "|The First State Bank |Barboursville|3-Apr-20 |\n",
- "|Ericson State Bank |Ericson |14-Feb-20 |\n",
- "|City National Bank of New Jersey|Newark |1-Nov-19 |\n",
- "|Resolute Bank |Maumee |25-Oct-19 |\n",
- "+--------------------------------+-------------+------------+\n",
- "only showing top 4 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df.createOrReplaceTempView(\"banklist\")\n",
- "\n",
- "df_check = spark.sql('''select `Bank Name`, City, `Closing Date` from banklist''')\n",
- "df_check.show(4, truncate=False)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "A_h4nezoVoMP"
- },
- "source": [
- "## **4 Dataframe Basic Operations**"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "NLoqnwVgtucp"
- },
- "source": [
- "### 4.1 Describe dataframe"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "LJSOwS4Eturw",
- "outputId": "196643d7-35c5-4393-9ee0-95962684f637"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+-------+--------------------+-------+----+-----------------+---------------------+------------+\n",
- "|summary| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|\n",
- "+-------+--------------------+-------+----+-----------------+---------------------+------------+\n",
- "| count| 561| 561| 561| 561| 561| 561|\n",
- "| mean| null| null|null|31685.68449197861| null| null|\n",
- "| stddev| null| null|null|16446.65659309965| null| null|\n",
- "| min|1st American Stat...|Acworth| AL| 91| 1st United Bank| 1-Aug-08|\n",
- "| max| ebank|Wyoming| WY| 58701| Your Community Bank| 9-Sep-11|\n",
- "+-------+--------------------+-------+----+-----------------+---------------------+------------+\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df.describe().show()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "FwVXN5fZn3Jz",
- "outputId": "8a0fa666-647a-4939-934a-8460e06c5447"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+-------+-------+----+\n",
- "|summary| City| ST|\n",
- "+-------+-------+----+\n",
- "| count| 561| 561|\n",
- "| mean| null|null|\n",
- "| stddev| null|null|\n",
- "| min|Acworth| AL|\n",
- "| max|Wyoming| WY|\n",
- "+-------+-------+----+\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df.describe('City', 'ST').show()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "RDht33CnhVL5"
- },
- "source": [
- "### 4.2 Counts, Columns and Schema"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "O63DzXi1VoaN",
- "outputId": "0961aac2-74f3-4a70-c281-4ed74d575053"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "df.count\t\t: 561\n",
- "df.columns\t: ['Bank Name', 'City', 'ST', 'CERT', 'Acquiring Institution', 'Closing Date']\n",
- "df dtypes\t: [('Bank Name', 'string'), ('City', 'string'), ('ST', 'string'), ('CERT', 'int'), ('Acquiring Institution', 'string'), ('Closing Date', 'string')]\n",
- "df schema 1: StructType([StructField('Bank Name', StringType(), True), StructField('City', StringType(), True), StructField('ST', StringType(), True), StructField('CERT', IntegerType(), True), StructField('Acquiring Institution', StringType(), True), StructField('Closing Date', StringType(), True)])\n"
- ]
- }
- ],
- "source": [
- "print('df.count\t\t:', df.count())\n",
- "print('df.columns\t:', df.columns)\n",
- "print('df dtypes\t:', df.dtypes)\n",
- "print('df schema 1:', df.schema)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "AeG5OcIq1vfg",
- "outputId": "97ffca11-b0e7-4887-c7ed-a8bd9e2ff5b2"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "df schema 1:\n",
- "root\n",
- " |-- Bank Name: string (nullable = true)\n",
- " |-- City: string (nullable = true)\n",
- " |-- ST: string (nullable = true)\n",
- " |-- CERT: integer (nullable = true)\n",
- " |-- Acquiring Institution: string (nullable = true)\n",
- " |-- Closing Date: string (nullable = true)\n",
- "\n"
- ]
- }
- ],
- "source": [
- "print('df schema 1:')\n",
- "df.printSchema()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "OSHkkGVBhd-F"
- },
- "source": [
- "### 4.3 Remove Duplicates"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "CcqzJ65IV0Fa",
- "outputId": "3b77c35f-4010-4a6a-b409-c764a7000d2f"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "df.count\t\t: 561\n",
- "df.columns\t: ['Bank Name', 'City', 'ST', 'CERT', 'Acquiring Institution', 'Closing Date']\n"
- ]
- }
- ],
- "source": [
- "df = df.dropDuplicates()\n",
- "print('df.count\t\t:', df.count())\n",
- "print('df.columns\t:', df.columns)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "olIfm2KIicOn"
- },
- "source": [
- "### 4.4 Select specific columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "3wBMsReAWSUF",
- "outputId": "2d75977f-77d8-4a3f-cb70-780a8ccfd05d"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+\n",
- "| Bank Name| City|\n",
- "+--------------------+--------+\n",
- "| First Bank of Idaho| Ketchum|\n",
- "|Amcore Bank, Nati...|Rockford|\n",
- "+--------------------+--------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.select(*['Bank Name', 'City'])\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "WMvFVdP_oK7W"
- },
- "source": [
- "### 4.5 Select multiple columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "fS3tpP6qoLVu",
- "outputId": "73bcacce-8016-4ff8-bae0-0ce89be7f5cd"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+---------------------+--------+------------+--------------------+\n",
- "|Acquiring Institution| City|Closing Date| Bank Name|\n",
- "+---------------------+--------+------------+--------------------+\n",
- "| U.S. Bank, N.A.| Ketchum| 24-Apr-09| First Bank of Idaho|\n",
- "| Harris N.A.|Rockford| 23-Apr-10|Amcore Bank, Nati...|\n",
- "+---------------------+--------+------------+--------------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "col_l = list(set(df.columns) - {'CERT','ST'})\n",
- "df2 = df.select(*col_l)\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "Zfc5uWaoi_R2"
- },
- "source": [
- "### 4.6 Rename columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "PdOkLYzlisvy",
- "outputId": "5172404f-8533-4a28-bb9c-4cdb0576280d"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+-----+-----+---------------+------------+\n",
- "| bank_name| City|state| cert|acq_institution|closing_date|\n",
- "+--------------------+--------+-----+-----+---------------+------------+\n",
- "| First Bank of Idaho| Ketchum| ID|34396|U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+-----+-----+---------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df \\\n",
- " .withColumnRenamed('Bank Name' , 'bank_name') \\\n",
- " .withColumnRenamed('Acquiring Institution', 'acq_institution') \\\n",
- " .withColumnRenamed('Closing Date' , 'closing_date') \\\n",
- " .withColumnRenamed('ST' , 'state') \\\n",
- " .withColumnRenamed('CERT' , 'cert') #\\\n",
- "\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "veAUD18tl6oG"
- },
- "source": [
- "### 4.7 Rename columns using loop"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "0gnKDBPjjpka",
- "outputId": "d72eb7fa-e2cc-48c2-c487-f5eff71b6982"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| Bank_Name| City| ST| CERT|Acquiring_Institution|Closing_Date|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| ID|34396| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "rename_expr = [col(column).alias(column.replace(' ', '_')) for column in df.columns]\n",
- "\n",
- "df2 = df.select(*rename_expr)\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "momxuupJnqPd"
- },
- "source": [
- "### 4.8 Add columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "uDKwdHg5l_nm",
- "outputId": "523ec74f-d6c1-43d2-bd6c-a1ff1b7dde78"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---+-----+---------------------+------------+-----+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|state|\n",
- "+--------------------+--------+---+-----+---------------------+------------+-----+\n",
- "| First Bank of Idaho| Ketchum| ID|34396| U.S. Bank, N.A.| 24-Apr-09| ID|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10| IL|\n",
- "+--------------------+--------+---+-----+---------------------+------------+-----+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.withColumn('state', col('ST'))\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "EjkXUUpvou7B"
- },
- "source": [
- "### 4.9 Add constant column"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "0-gSou1GnpBd",
- "outputId": "50611507-a1ac-4799-f9dd-35582acfd4ea"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---+-----+---------------------+------------+-------+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|country|\n",
- "+--------------------+--------+---+-----+---------------------+------------+-------+\n",
- "| First Bank of Idaho| Ketchum| ID|34396| U.S. Bank, N.A.| 24-Apr-09| US|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10| US|\n",
- "+--------------------+--------+---+-----+---------------------+------------+-------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.withColumn('country', lit('US'))\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "wx7fAtmqZxSH"
- },
- "source": [
- "### 4.10 Drop columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "fAKuWe7nZxmc",
- "outputId": "77278d54-efe0-4c4f-989f-ad3a4f701fea"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---+---------------------+------------+\n",
- "| Bank Name| City| ST|Acquiring Institution|Closing Date|\n",
- "+--------------------+--------+---+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| ID| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| IL| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.drop('CERT')\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "AG7tuEZpaGll"
- },
- "source": [
- "### 4.11 Drop multiple columns"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "56E1uJPQpZJH",
- "outputId": "8c3d1e2e-f984-44a5-d6fa-9aa0a013febf"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---------------------+------------+\n",
- "| Bank Name| City|Acquiring Institution|Closing Date|\n",
- "+--------------------+--------+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.drop(*['CERT','ST'])\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "WuVEE3SqaFvC",
- "outputId": "9b4c70e2-8812-4282-fdc9-84c0dd435bf3"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---------------------+------------+\n",
- "| Bank Name| City|Acquiring Institution|Closing Date|\n",
- "+--------------------+--------+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = reduce(DataFrame.drop, ['CERT','ST'], df)\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "PhuwX3AwbRiu"
- },
- "source": [
- "### 4.12 Filter data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 27,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "yeA5BOpJbD5O",
- "outputId": "95398d26-e396-4b64-fae1-feb8a3b56386"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "df.count : 561\n",
- "df2.count : 4\n",
- "df3.count : 9\n",
- "df4.count : 73\n"
- ]
- }
- ],
- "source": [
- "# Equal to values\n",
- "df2 = df.where(df['ST'] == 'NE')\n",
- "\n",
- "# Between values\n",
- "df3 = df.where(df['CERT'].between('1000','2000'))\n",
- "\n",
- "# Is inside multiple values\n",
- "df4 = df.where(df['ST'].isin('NE','IL'))\n",
- "\n",
- "print('df.count :', df.count())\n",
- "print('df2.count :', df2.count())\n",
- "print('df3.count :', df3.count())\n",
- "print('df4.count :', df4.count())\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 28,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "k0fL-hmR7XAU",
- "outputId": "0b6c1a97-fc04-48b9-b810-105bfd34df70"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "df2 sample below\n",
- "+-------------------+---------+---+-----+---------------------+------------+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|\n",
- "+-------------------+---------+---+-----+---------------------+------------+\n",
- "| TierOne Bank| Lincoln| NE|29341| Great Western Bank| 4-Jun-10|\n",
- "|Sherman County Bank|Loup City| NE| 5431| Heritage Bank| 13-Feb-09|\n",
- "+-------------------+---------+---+-----+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# Equal to values\n",
- "df2 = df.where(df['ST'] == 'NE')\n",
- "\n",
- "print('\\ndf2 sample below')\n",
- "df2.show(2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "WvyiT6Virnk0"
- },
- "source": [
- "### 4.13 Filter data using logical operators"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 29,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "d2jx8gV3q70-",
- "outputId": "6ae8b94b-6658-4bbf-bba8-4821dc291c1f"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+------------------+-------+---+-----+---------------------+------------+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|\n",
- "+------------------+-------+---+-----+---------------------+------------+\n",
- "|Ericson State Bank|Ericson| NE|18265| Farmers and Merch...| 14-Feb-20|\n",
- "+------------------+-------+---+-----+---------------------+------------+\n",
- "\n"
- ]
- }
- ],
- "source": [
- "df2 = df.where((df['ST'] == 'NE') & (df['City'] == 'Ericson'))\n",
- "df2.show(3)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "bImSbNBFcsNl"
- },
- "source": [
- "### 4.14 Cast datatypes"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 30,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "5kUFFW4FcsNp",
- "outputId": "36c86cf4-0c22-45ca-ed38-bbe129e5e560"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "==================================================\n",
- "Pre cast\n",
- "root\n",
- " |-- Bank Name: string (nullable = true)\n",
- " |-- City: string (nullable = true)\n",
- " |-- ST: string (nullable = true)\n",
- " |-- CERT: integer (nullable = true)\n",
- " |-- Acquiring Institution: string (nullable = true)\n",
- " |-- Closing Date: string (nullable = true)\n",
- "\n",
- "None\n",
- "==================================================\n",
- "Post cast\n",
- "root\n",
- " |-- Bank Name: string (nullable = true)\n",
- " |-- City: string (nullable = true)\n",
- " |-- ST: string (nullable = true)\n",
- " |-- CERT: integer (nullable = true)\n",
- " |-- Acquiring Institution: string (nullable = true)\n",
- " |-- Closing Date: string (nullable = true)\n",
- " |-- CERT_str1: string (nullable = true)\n",
- " |-- CERT_str2: string (nullable = true)\n",
- "\n",
- "None\n"
- ]
- }
- ],
- "source": [
- "print('='*50)\n",
- "print('Pre cast')\n",
- "print(df.printSchema())\n",
- "\n",
- "df2 = df \\\n",
- ".withColumn('CERT_str1', df['CERT'].cast('string')) \\\n",
- ".withColumn('CERT_str2', df['CERT'].cast(StringType())) #\\\n",
- "\n",
- "print('='*50)\n",
- "print('Post cast')\n",
- "print(df2.printSchema())\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "BOAWTJcIVLrs"
- },
- "source": [
- "### 4.15 Replace values in dataframe"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 31,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "vJkLrgi-VMqM",
- "outputId": "c9c09051-10ef-4234-d2e9-37a7cc202d87"
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| ID|34396| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n",
- "Replace 7 in the above dataframe with 17 at all instances\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| Bank Name| City| ST| CERT|Acquiring Institution|Closing Date|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "| First Bank of Idaho| Ketchum| ID|34396| U.S. Bank, N.A.| 24-Apr-09|\n",
- "|Amcore Bank, Nati...|Rockford| IL| 3735| Harris N.A.| 23-Apr-10|\n",
- "+--------------------+--------+---+-----+---------------------+------------+\n",
- "only showing top 2 rows\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# Pre replace\n",
- "df.show(2)\n",
- "\n",
- "# Post replace\n",
- "print('Replace 7 in the above dataframe with 17 at all instances')\n",
- "df.na.replace(7,17).show(2)"
- ]
- }
- ],
- "metadata": {
- "colab": {
- "provenance": [],
- "toc_visible": true
- },
- "kernelspec": {
- "display_name": "Python 3",
- "name": "python3"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}
diff --git a/PySpark_Dataframe_Commom_Data_Operatorios.ipynb b/PySpark_Dataframe_Commom_Data_Operatorios.ipynb
deleted file mode 100644
index 1b69940..0000000
--- a/PySpark_Dataframe_Commom_Data_Operatorios.ipynb
+++ /dev/null
@@ -1,569 +0,0 @@
-{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "colab": {
- "provenance": []
- },
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- },
- "language_info": {
- "name": "python"
- }
- },
- "cells": [
- {
- "cell_type": "markdown",
- "source": [
- "# Creating New Column in PySpark DataFrame"
- ],
- "metadata": {
- "id": "PgHnsi52fTxr"
- }
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Installing Libraries, Importing the Libraries and Creating Spark Session"
- ],
- "metadata": {
- "id": "xD2_W_08fXs_"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "!pip install pyspark\n",
- "import pyspark\n",
- "from pyspark.sql import SparkSession\n",
- "spark=SparkSession.builder.appName(\"pysparkdf\").getOrCreate()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "RP1guNIYe2U7",
- "outputId": "b8f248e5-2ae2-47e5-b5df-f70117e3481d"
- },
- "execution_count": 1,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Collecting pyspark\n",
- " Downloading pyspark-3.4.1.tar.gz (310.8 MB)\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.8/310.8 MB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- "Requirement already satisfied: py4j==0.10.9.7 in /usr/local/lib/python3.10/dist-packages (from pyspark) (0.10.9.7)\n",
- "Building wheels for collected packages: pyspark\n",
- " Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- " Created wheel for pyspark: filename=pyspark-3.4.1-py2.py3-none-any.whl size=311285398 sha256=115e6c8daeb33de125d001c462a71282203f6c1fd4b93692ca6a751c13036e2e\n",
- " Stored in directory: /root/.cache/pip/wheels/0d/77/a3/ff2f74cc9ab41f8f594dabf0579c2a7c6de920d584206e0834\n",
- "Successfully built pyspark\n",
- "Installing collected packages: pyspark\n",
- "Successfully installed pyspark-3.4.1\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Importing Data"
- ],
- "metadata": {
- "id": "7I3EIkpnfrrT"
- }
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {
- "id": "0AMDPqUkesch"
- },
- "outputs": [],
- "source": [
- "df = spark.read.csv('cereal.csv', sep = ',', inferSchema = True, header = True)"
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## Reading the Schema"
- ],
- "metadata": {
- "id": "ucoOWQ1NfuZp"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "l9ZEXMCKfxoE",
- "outputId": "65534ccd-829c-43a9-b419-d3316154d2a6"
- },
- "execution_count": 3,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- name: string (nullable = true)\n",
- " |-- mfr: string (nullable = true)\n",
- " |-- type: string (nullable = true)\n",
- " |-- calories: integer (nullable = true)\n",
- " |-- protein: integer (nullable = true)\n",
- " |-- fat: integer (nullable = true)\n",
- " |-- sodium: integer (nullable = true)\n",
- " |-- fiber: double (nullable = true)\n",
- " |-- carbo: double (nullable = true)\n",
- " |-- sugars: integer (nullable = true)\n",
- " |-- potass: integer (nullable = true)\n",
- " |-- vitamins: integer (nullable = true)\n",
- " |-- shelf: integer (nullable = true)\n",
- " |-- weight: double (nullable = true)\n",
- " |-- cups: double (nullable = true)\n",
- " |-- rating: double (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# select()"
- ],
- "metadata": {
- "id": "8CryY4XBg2Dy"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.select('name', 'mfr', 'rating').show(10)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "4qEK9Hh-f5z5",
- "outputId": "84b9939d-83bd-49cb-8b36-a87248aba6e0"
- },
- "execution_count": 4,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+---+---------+\n",
- "| name|mfr| rating|\n",
- "+--------------------+---+---------+\n",
- "| 100% Bran| N|68.402973|\n",
- "| 100% Natural Bran| Q|33.983679|\n",
- "| All-Bran| K|59.425505|\n",
- "|All-Bran with Ext...| K|93.704912|\n",
- "| Almond Delight| R|34.384843|\n",
- "|Apple Cinnamon Ch...| G|29.509541|\n",
- "| Apple Jacks| K|33.174094|\n",
- "| Basic 4| G|37.038562|\n",
- "| Bran Chex| R|49.120253|\n",
- "| Bran Flakes| P|53.313813|\n",
- "+--------------------+---+---------+\n",
- "only showing top 10 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# withColumn()"
- ],
- "metadata": {
- "id": "YFkz5fi3g4rN"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.withColumn(\"Calories\",df['calories'].cast(\"Integer\")).printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Kym19ml9f9Ui",
- "outputId": "72fc23fe-acd9-4c13-894d-651d012044e8"
- },
- "execution_count": 5,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- name: string (nullable = true)\n",
- " |-- mfr: string (nullable = true)\n",
- " |-- type: string (nullable = true)\n",
- " |-- Calories: integer (nullable = true)\n",
- " |-- protein: integer (nullable = true)\n",
- " |-- fat: integer (nullable = true)\n",
- " |-- sodium: integer (nullable = true)\n",
- " |-- fiber: double (nullable = true)\n",
- " |-- carbo: double (nullable = true)\n",
- " |-- sugars: integer (nullable = true)\n",
- " |-- potass: integer (nullable = true)\n",
- " |-- vitamins: integer (nullable = true)\n",
- " |-- shelf: integer (nullable = true)\n",
- " |-- weight: double (nullable = true)\n",
- " |-- cups: double (nullable = true)\n",
- " |-- rating: double (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# groupBy()"
- ],
- "metadata": {
- "id": "Avu4Pd5Qg7Fh"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.groupBy(\"name\", \"calories\").count().show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "RYs1skB4f_mB",
- "outputId": "ad33c3f3-5626-45c7-8a0e-7a66d7015de4"
- },
- "execution_count": 6,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+--------+-----+\n",
- "| name|calories|count|\n",
- "+--------------------+--------+-----+\n",
- "|Just Right Fruit ...| 140| 1|\n",
- "| Raisin Bran| 120| 1|\n",
- "|Shredded Wheat sp...| 90| 1|\n",
- "| Corn Pops| 110| 1|\n",
- "| Honey Nut Cheerios| 110| 1|\n",
- "|Muesli Raisins; D...| 150| 1|\n",
- "| Fruity Pebbles| 110| 1|\n",
- "| 100% Bran| 70| 1|\n",
- "| Fruitful Bran| 120| 1|\n",
- "| Puffed Rice| 50| 1|\n",
- "| Raisin Squares| 90| 1|\n",
- "| Total Raisin Bran| 140| 1|\n",
- "| Golden Grahams| 110| 1|\n",
- "| Nutri-grain Wheat| 90| 1|\n",
- "| 100% Natural Bran| 120| 1|\n",
- "|Apple Cinnamon Ch...| 110| 1|\n",
- "|Mueslix Crispy Blend| 160| 1|\n",
- "|Shredded Wheat 'n...| 90| 1|\n",
- "| Smacks| 110| 1|\n",
- "| Quaker Oatmeal| 100| 1|\n",
- "+--------------------+--------+-----+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# orderBy()"
- ],
- "metadata": {
- "id": "461dECcGg-Cc"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.orderBy(\"protein\").show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "mAsEHrKmgCC0",
- "outputId": "73abc952-78f0-4b4f-d014-4ac92ffb4611"
- },
- "execution_count": 7,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| name|mfr|type|calories|protein|fat|sodium|fiber|carbo|sugars|potass|vitamins|shelf|weight|cups| rating|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| Cap'n'Crunch| Q| C| 120| 1| 2| 220| 0.0| 12.0| 12| 35| 25| 2| 1.0|0.75|18.042851|\n",
- "|Cinnamon Toast Cr...| G| C| 120| 1| 3| 210| 0.0| 13.0| 9| 45| 25| 2| 1.0|0.75|19.823573|\n",
- "| Cocoa Puffs| G| C| 110| 1| 1| 180| 0.0| 12.0| 13| 55| 25| 2| 1.0| 1.0|22.736446|\n",
- "| Corn Pops| K| C| 110| 1| 0| 90| 1.0| 13.0| 12| 20| 25| 2| 1.0| 1.0|35.782791|\n",
- "| Count Chocula| G| C| 110| 1| 1| 180| 0.0| 12.0| 13| 65| 25| 2| 1.0| 1.0|22.396513|\n",
- "| Frosted Flakes| K| C| 110| 1| 0| 200| 1.0| 14.0| 11| 25| 25| 1| 1.0|0.75|31.435973|\n",
- "| Fruity Pebbles| P| C| 110| 1| 1| 135| 0.0| 13.0| 12| 25| 25| 2| 1.0|0.75|28.025765|\n",
- "| Golden Grahams| G| C| 110| 1| 1| 280| 0.0| 15.0| 9| 45| 25| 2| 1.0|0.75|23.804043|\n",
- "| Honey Graham Ohs| Q| C| 120| 1| 2| 220| 1.0| 12.0| 11| 45| 25| 2| 1.0| 1.0|21.871292|\n",
- "| Honey-comb| P| C| 110| 1| 0| 180| 0.0| 14.0| 11| 35| 25| 1| 1.0|1.33|28.742414|\n",
- "| Puffed Rice| Q| C| 50| 1| 0| 0| 0.0| 13.0| 0| 15| 0| 3| 0.5| 1.0|60.756112|\n",
- "| Rice Chex| R| C| 110| 1| 0| 240| 0.0| 23.0| 2| 30| 25| 1| 1.0|1.13|41.998933|\n",
- "| Trix| G| C| 110| 1| 1| 140| 0.0| 13.0| 12| 25| 25| 2| 1.0| 1.0|27.753301|\n",
- "| Froot Loops| K| C| 110| 2| 1| 125| 1.0| 11.0| 13| 30| 25| 2| 1.0| 1.0|32.207582|\n",
- "|Apple Cinnamon Ch...| G| C| 110| 2| 2| 180| 1.5| 10.5| 10| 70| 25| 1| 1.0|0.75|29.509541|\n",
- "| Crispix| K| C| 110| 2| 0| 220| 1.0| 21.0| 3| 30| 25| 3| 1.0| 1.0|46.895644|\n",
- "| Apple Jacks| K| C| 110| 2| 0| 125| 1.0| 11.0| 14| 30| 25| 2| 1.0| 1.0|33.174094|\n",
- "| Corn Flakes| K| C| 100| 2| 0| 290| 1.0| 21.0| 2| 35| 25| 1| 1.0| 1.0|45.863324|\n",
- "| Golden Crisp| P| C| 100| 2| 0| 45| 0.0| 11.0| 15| 40| 25| 1| 1.0|0.88|35.252444|\n",
- "|Crispy Wheat & Ra...| G| C| 100| 2| 1| 140| 2.0| 11.0| 10| 120| 25| 3| 1.0|0.75|36.176196|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# when()"
- ],
- "metadata": {
- "id": "ZvoLjFLlhC2y"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "from pyspark.sql.functions import when"
- ],
- "metadata": {
- "id": "0BkjHZaLggtb"
- },
- "execution_count": 14,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "df.select(\"name\", when(df.vitamins >= \"25\", \"rich in vitamins\")).show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "5gta6F8fgeVO",
- "outputId": "6efa5fd8-8d12-42b1-9d3d-5dcaebb09a06"
- },
- "execution_count": 15,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+----------------------------------------------------+\n",
- "| name|CASE WHEN (vitamins >= 25) THEN rich in vitamins END|\n",
- "+--------------------+----------------------------------------------------+\n",
- "| 100% Bran| rich in vitamins|\n",
- "| 100% Natural Bran| null|\n",
- "| All-Bran| rich in vitamins|\n",
- "|All-Bran with Ext...| rich in vitamins|\n",
- "| Almond Delight| rich in vitamins|\n",
- "|Apple Cinnamon Ch...| rich in vitamins|\n",
- "| Apple Jacks| rich in vitamins|\n",
- "| Basic 4| rich in vitamins|\n",
- "| Bran Chex| rich in vitamins|\n",
- "| Bran Flakes| rich in vitamins|\n",
- "| Cap'n'Crunch| rich in vitamins|\n",
- "| Cheerios| rich in vitamins|\n",
- "|Cinnamon Toast Cr...| rich in vitamins|\n",
- "| Clusters| rich in vitamins|\n",
- "| Cocoa Puffs| rich in vitamins|\n",
- "| Corn Chex| rich in vitamins|\n",
- "| Corn Flakes| rich in vitamins|\n",
- "| Corn Pops| rich in vitamins|\n",
- "| Count Chocula| rich in vitamins|\n",
- "| Cracklin' Oat Bran| rich in vitamins|\n",
- "+--------------------+----------------------------------------------------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# filter()"
- ],
- "metadata": {
- "id": "oCNE9jk7hF_f"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.filter(df.calories == \"100\").show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "kjVLOMBvgjwn",
- "outputId": "7a689dff-5137-4630-950d-9a223b2946fa"
- },
- "execution_count": 16,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| name|mfr|type|calories|protein|fat|sodium|fiber|carbo|sugars|potass|vitamins|shelf|weight|cups| rating|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| Corn Flakes| K| C| 100| 2| 0| 290| 1.0| 21.0| 2| 35| 25| 1| 1.0| 1.0|45.863324|\n",
- "|Cream of Wheat (Q...| N| H| 100| 3| 0| 80| 1.0| 21.0| 0| -1| 0| 2| 1.0| 1.0|64.533816|\n",
- "|Crispy Wheat & Ra...| G| C| 100| 2| 1| 140| 2.0| 11.0| 10| 120| 25| 3| 1.0|0.75|36.176196|\n",
- "| Double Chex| R| C| 100| 2| 0| 190| 1.0| 18.0| 5| 80| 25| 3| 1.0|0.75|44.330856|\n",
- "| Frosted Mini-Wheats| K| C| 100| 3| 0| 0| 3.0| 14.0| 7| 100| 25| 2| 1.0| 0.8|58.345141|\n",
- "| Golden Crisp| P| C| 100| 2| 0| 45| 0.0| 11.0| 15| 40| 25| 1| 1.0|0.88|35.252444|\n",
- "| Grape Nuts Flakes| P| C| 100| 3| 1| 140| 3.0| 15.0| 5| 85| 25| 3| 1.0|0.88|52.076897|\n",
- "| Life| Q| C| 100| 4| 2| 150| 2.0| 12.0| 6| 95| 25| 2| 1.0|0.67|45.328074|\n",
- "| Maypo| A| H| 100| 4| 1| 0| 0.0| 16.0| 3| 95| 25| 2| 1.0| 1.0|54.850917|\n",
- "|Multi-Grain Cheerios| G| C| 100| 2| 1| 220| 2.0| 15.0| 6| 90| 25| 1| 1.0| 1.0|40.105965|\n",
- "| Product 19| K| C| 100| 3| 0| 320| 1.0| 20.0| 3| 45| 100| 3| 1.0| 1.0| 41.50354|\n",
- "| Quaker Oat Squares| Q| C| 100| 4| 1| 135| 2.0| 14.0| 6| 110| 25| 3| 1.0| 0.5|49.511874|\n",
- "| Quaker Oatmeal| Q| H| 100| 5| 2| 0| 2.7| -1.0| -1| 110| 0| 1| 1.0|0.67|50.828392|\n",
- "| Raisin Nut Bran| G| C| 100| 3| 2| 140| 2.5| 10.5| 8| 140| 25| 3| 1.0| 0.5| 39.7034|\n",
- "| Total Whole Grain| G| C| 100| 3| 1| 200| 3.0| 16.0| 3| 110| 100| 3| 1.0| 1.0|46.658844|\n",
- "| Wheat Chex| R| C| 100| 3| 1| 230| 3.0| 17.0| 3| 115| 25| 1| 1.0|0.67|49.787445|\n",
- "| Wheaties| G| C| 100| 3| 1| 200| 3.0| 17.0| 3| 110| 25| 1| 1.0| 1.0|51.592193|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# isNull()/isNotNull()"
- ],
- "metadata": {
- "id": "-HRkuU4dhImn"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "#isNotNull()\n",
- "from pyspark.sql.functions import *\n",
- "#filter data by null values\n",
- "df.filter(df.name.isNotNull()).show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "vnN4l9nTgnFL",
- "outputId": "832d73ad-563f-45f3-e4f1-f0d3124c6f4d"
- },
- "execution_count": 17,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| name|mfr|type|calories|protein|fat|sodium|fiber|carbo|sugars|potass|vitamins|shelf|weight|cups| rating|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "| 100% Bran| N| C| 70| 4| 1| 130| 10.0| 5.0| 6| 280| 25| 3| 1.0|0.33|68.402973|\n",
- "| 100% Natural Bran| Q| C| 120| 3| 5| 15| 2.0| 8.0| 8| 135| 0| 3| 1.0| 1.0|33.983679|\n",
- "| All-Bran| K| C| 70| 4| 1| 260| 9.0| 7.0| 5| 320| 25| 3| 1.0|0.33|59.425505|\n",
- "|All-Bran with Ext...| K| C| 50| 4| 0| 140| 14.0| 8.0| 0| 330| 25| 3| 1.0| 0.5|93.704912|\n",
- "| Almond Delight| R| C| 110| 2| 2| 200| 1.0| 14.0| 8| -1| 25| 3| 1.0|0.75|34.384843|\n",
- "|Apple Cinnamon Ch...| G| C| 110| 2| 2| 180| 1.5| 10.5| 10| 70| 25| 1| 1.0|0.75|29.509541|\n",
- "| Apple Jacks| K| C| 110| 2| 0| 125| 1.0| 11.0| 14| 30| 25| 2| 1.0| 1.0|33.174094|\n",
- "| Basic 4| G| C| 130| 3| 2| 210| 2.0| 18.0| 8| 100| 25| 3| 1.33|0.75|37.038562|\n",
- "| Bran Chex| R| C| 90| 2| 1| 200| 4.0| 15.0| 6| 125| 25| 1| 1.0|0.67|49.120253|\n",
- "| Bran Flakes| P| C| 90| 3| 0| 210| 5.0| 13.0| 5| 190| 25| 3| 1.0|0.67|53.313813|\n",
- "| Cap'n'Crunch| Q| C| 120| 1| 2| 220| 0.0| 12.0| 12| 35| 25| 2| 1.0|0.75|18.042851|\n",
- "| Cheerios| G| C| 110| 6| 2| 290| 2.0| 17.0| 1| 105| 25| 1| 1.0|1.25|50.764999|\n",
- "|Cinnamon Toast Cr...| G| C| 120| 1| 3| 210| 0.0| 13.0| 9| 45| 25| 2| 1.0|0.75|19.823573|\n",
- "| Clusters| G| C| 110| 3| 2| 140| 2.0| 13.0| 7| 105| 25| 3| 1.0| 0.5|40.400208|\n",
- "| Cocoa Puffs| G| C| 110| 1| 1| 180| 0.0| 12.0| 13| 55| 25| 2| 1.0| 1.0|22.736446|\n",
- "| Corn Chex| R| C| 110| 2| 0| 280| 0.0| 22.0| 3| 25| 25| 1| 1.0| 1.0|41.445019|\n",
- "| Corn Flakes| K| C| 100| 2| 0| 290| 1.0| 21.0| 2| 35| 25| 1| 1.0| 1.0|45.863324|\n",
- "| Corn Pops| K| C| 110| 1| 0| 90| 1.0| 13.0| 12| 20| 25| 2| 1.0| 1.0|35.782791|\n",
- "| Count Chocula| G| C| 110| 1| 1| 180| 0.0| 12.0| 13| 65| 25| 2| 1.0| 1.0|22.396513|\n",
- "| Cracklin' Oat Bran| K| C| 110| 3| 3| 140| 4.0| 10.0| 7| 160| 25| 3| 1.0| 0.5|40.448772|\n",
- "+--------------------+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+---------+\n",
- "only showing top 20 rows\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# isNull()"
- ],
- "metadata": {
- "id": "UhlLFymIhNDd"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df.filter(df.name.isNull()).show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "uFiatSsOgpUs",
- "outputId": "9a655b50-cf12-436d-c2ed-e94cc11677e7"
- },
- "execution_count": 18,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+----+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+------+\n",
- "|name|mfr|type|calories|protein|fat|sodium|fiber|carbo|sugars|potass|vitamins|shelf|weight|cups|rating|\n",
- "+----+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+------+\n",
- "+----+---+----+--------+-------+---+------+-----+-----+------+------+--------+-----+------+----+------+\n",
- "\n"
- ]
- }
- ]
- }
- ]
-}
\ No newline at end of file
diff --git a/PySpark_RDD e DataFrame.ipynb b/PySpark_RDD e DataFrame.ipynb
deleted file mode 100644
index 1d676b0..0000000
--- a/PySpark_RDD e DataFrame.ipynb
+++ /dev/null
@@ -1,496 +0,0 @@
-{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "colab": {
- "provenance": [],
- "toc_visible": true
- },
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- },
- "language_info": {
- "name": "python"
- }
- },
- "cells": [
- {
- "cell_type": "markdown",
- "source": [
- "# Configuração de biblioteca do PySpark no Google"
- ],
- "metadata": {
- "id": "kT5SPWFMVURY"
- }
- },
- {
- "cell_type": "code",
- "execution_count": 28,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Zdd7ESWeS3U1",
- "outputId": "dba2e0d4-cfab-4d0f-dc73-26d1d212aefb"
- },
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Requirement already satisfied: pyspark in /usr/local/lib/python3.10/dist-packages (3.4.1)\n",
- "Requirement already satisfied: py4j==0.10.9.7 in /usr/local/lib/python3.10/dist-packages (from pyspark) (0.10.9.7)\n"
- ]
- }
- ],
- "source": [
- "!pip install pyspark"
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Criando a sessão do SparkContext e SparkSession"
- ],
- "metadata": {
- "id": "iXZzK_F0VW5R"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "from pyspark import SparkContext\n",
- "from pyspark.sql import SparkSession"
- ],
- "metadata": {
- "id": "SVC51xpOTF4h"
- },
- "execution_count": 29,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "sc = SparkContext.getOrCreate()"
- ],
- "metadata": {
- "id": "uNjNxORcTKEb"
- },
- "execution_count": 30,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "spark = SparkSession.builder.appName('PySpark DataFrame From RDD').getOrCreate()"
- ],
- "metadata": {
- "id": "MgwbLZPBTMJF"
- },
- "execution_count": 31,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Create PySpark DataFrame From an Existing RDD"
- ],
- "metadata": {
- "id": "NqmeysoNTsw9"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "rdd = sc.parallelize([('C',85,76,87,91), ('B',85,76,87,91), (\"A\", 85,78,96,92), (\"A\", 92,76,89,96)], 4)"
- ],
- "metadata": {
- "id": "LbGDD240TOz3"
- },
- "execution_count": 32,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "print(type(rdd))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "5xUhfDpLTSFX",
- "outputId": "d4b024c7-98cc-403a-a21c-c98bc79086fc"
- },
- "execution_count": 33,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "sub = ['Division','English','Mathematics','Physics','Chemistry']\n",
- "marks_df = spark.createDataFrame(rdd, schema=sub)"
- ],
- "metadata": {
- "id": "NGzl22XDTUxf"
- },
- "execution_count": 34,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "print(type(marks_df))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "w9CrNRlPTW0b",
- "outputId": "936c9592-4de1-4d71-9216-7a70d1ffe7a5"
- },
- "execution_count": 35,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "marks_df.printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "H94oSH23TYp9",
- "outputId": "b62ae417-1966-4d50-fef4-cf65799f53d8"
- },
- "execution_count": 36,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- Division: string (nullable = true)\n",
- " |-- English: long (nullable = true)\n",
- " |-- Mathematics: long (nullable = true)\n",
- " |-- Physics: long (nullable = true)\n",
- " |-- Chemistry: long (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "marks_df.show()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Sf4pHHZfTbD_",
- "outputId": "863fc2a4-81f0-42d4-a68d-421278299e2d"
- },
- "execution_count": 37,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "+--------+-------+-----------+-------+---------+\n",
- "|Division|English|Mathematics|Physics|Chemistry|\n",
- "+--------+-------+-----------+-------+---------+\n",
- "| C| 85| 76| 87| 91|\n",
- "| B| 85| 76| 87| 91|\n",
- "| A| 85| 78| 96| 92|\n",
- "| A| 92| 76| 89| 96|\n",
- "+--------+-------+-----------+-------+---------+\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Create PySpark DataFrame From an External File"
- ],
- "metadata": {
- "id": "G7tzGYFoTvvu"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "from pyspark.sql import SparkSession"
- ],
- "metadata": {
- "id": "M_rIOv_-TxtX"
- },
- "execution_count": 38,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "spark = SparkSession.builder.appName('PySpark DataFrame From External Files').getOrCreate()"
- ],
- "metadata": {
- "id": "56SR03IGTzdx"
- },
- "execution_count": 39,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "csv_file = spark.read.csv('Fish.csv', sep = ',', inferSchema = True, header = True)"
- ],
- "metadata": {
- "id": "DgUKPm9bT1IQ"
- },
- "execution_count": 40,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "txt_file = spark.read.text(\"example.txt\")"
- ],
- "metadata": {
- "id": "B3KPNVERUEsl"
- },
- "execution_count": 41,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "json_file = spark.read.json(\"sample.json\", multiLine=True)"
- ],
- "metadata": {
- "id": "lnEuj94PUUNO"
- },
- "execution_count": 42,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "print(type(csv_file))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "B0E4RZcsUXDg",
- "outputId": "57d37c63-eea9-441e-f897-1823b37b400d"
- },
- "execution_count": 43,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "print(type(txt_file))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "kmAUj9z_UYW_",
- "outputId": "f86d43ee-3a4d-4186-fdbf-cad562cc0c81"
- },
- "execution_count": 44,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "print(type(json_file))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "Miuoeo7VUaIN",
- "outputId": "5499c487-e973-4d22-f7f8-86d84d5306e3"
- },
- "execution_count": 45,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "csv_file.printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "iSoTE3sBUcXe",
- "outputId": "5aa960ab-18d5-4178-cea6-e0bfa67c7f6b"
- },
- "execution_count": 46,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- Species: string (nullable = true)\n",
- " |-- Weight: double (nullable = true)\n",
- " |-- Length1: double (nullable = true)\n",
- " |-- Length2: double (nullable = true)\n",
- " |-- Length3: double (nullable = true)\n",
- " |-- Height: double (nullable = true)\n",
- " |-- Width: double (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "txt_file.printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "9tPb1wJqUdmk",
- "outputId": "0b2869b6-05dc-4c2c-d063-8905e8f3bf17"
- },
- "execution_count": 47,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- value: string (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "json_file.printSchema()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "7WKa1jWrUfMw",
- "outputId": "fffafedb-8551-4d4e-af6b-7a8dd4ae5de2"
- },
- "execution_count": 48,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "root\n",
- " |-- employees: array (nullable = true)\n",
- " | |-- element: struct (containsNull = true)\n",
- " | | |-- firstName: string (nullable = true)\n",
- " | | |-- lastName: string (nullable = true)\n",
- "\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# PySpark DataFrame to Pandas DataFrame"
- ],
- "metadata": {
- "id": "TTYZQ1BuUm91"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "df = csv_file.toPandas()"
- ],
- "metadata": {
- "id": "-YkSgpyyUpLK"
- },
- "execution_count": 49,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "type(df)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "_oaFwM6tUrI4",
- "outputId": "823a8a51-c5e0-49a5-d290-e6e60811fcab"
- },
- "execution_count": 50,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "pandas.core.frame.DataFrame"
- ]
- },
- "metadata": {},
- "execution_count": 50
- }
- ]
- }
- ]
-}
\ No newline at end of file
diff --git a/README.md b/README.md
deleted file mode 100644
index 4a92e9d..0000000
--- a/README.md
+++ /dev/null
@@ -1,2 +0,0 @@
-# Pos_Tech_DTAT
-Repositório para todas as Fases contemplando os códigos utilizados nas disciplinas da Pós Tech em Data Analytics
diff --git a/Transformations_and_Actions_PySpark.ipynb b/Transformations_and_Actions_PySpark.ipynb
deleted file mode 100644
index ebb8a2e..0000000
--- a/Transformations_and_Actions_PySpark.ipynb
+++ /dev/null
@@ -1,701 +0,0 @@
-{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "colab": {
- "provenance": []
- },
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- },
- "language_info": {
- "name": "python"
- }
- },
- "cells": [
- {
- "cell_type": "markdown",
- "source": [
- "# Transformations PySpark"
- ],
- "metadata": {
- "id": "DtPi3zvhItBb"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "!pip install pyspark"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "gZ-JqwDpIzmN",
- "outputId": "ff8dac73-54f7-4cac-be41-be333e7daff4"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Collecting pyspark\n",
- " Downloading pyspark-3.4.1.tar.gz (310.8 MB)\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.8/310.8 MB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- "Requirement already satisfied: py4j==0.10.9.7 in /usr/local/lib/python3.10/dist-packages (from pyspark) (0.10.9.7)\n",
- "Building wheels for collected packages: pyspark\n",
- " Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
- " Created wheel for pyspark: filename=pyspark-3.4.1-py2.py3-none-any.whl size=311285398 sha256=d66abc130d9c7d43c9c5033160ad176e04f57309bfe070942d8e05295de3a3af\n",
- " Stored in directory: /root/.cache/pip/wheels/0d/77/a3/ff2f74cc9ab41f8f594dabf0579c2a7c6de920d584206e0834\n",
- "Successfully built pyspark\n",
- "Installing collected packages: pyspark\n",
- "Successfully installed pyspark-3.4.1\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "!pip install findspark"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "f3Md3fv3I_XG",
- "outputId": "93350244-ee93-405b-f2a9-88d3a103d553"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Collecting findspark\n",
- " Downloading findspark-2.0.1-py2.py3-none-any.whl (4.4 kB)\n",
- "Installing collected packages: findspark\n",
- "Successfully installed findspark-2.0.1\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "from pyspark import SparkContext\n",
- "from pyspark.sql import SparkSession"
- ],
- "metadata": {
- "id": "Qy0Z0nZHI8Wp"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "sc = SparkContext.getOrCreate()"
- ],
- "metadata": {
- "id": "5eQ7NvRzJ0uQ"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "spark = SparkSession.builder.appName('PySpark DataFrame From RDD').getOrCreate()"
- ],
- "metadata": {
- "id": "UZJ896PgJ2K1"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## map()"
- ],
- "metadata": {
- "id": "5pUVpU6yIwwQ"
- }
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "kYKiwxjzImXY",
- "outputId": "59ee24eb-61f1-4978-e805-b9d72e8e0dd2"
- },
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "[2, 4, 6, 8, 10]\n"
- ]
- }
- ],
- "source": [
- "data= [1, 2, 3, 4, 5]\n",
- "myRDD= sc.parallelize(data)\n",
- "#Returns a new RDD by multiplying all elements of parent RDD by 2\n",
- "newRDD= myRDD.map(lambda x: x*2)\n",
- "print(newRDD.collect())"
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## flatMap()"
- ],
- "metadata": {
- "id": "8iz2mvvkKDMn"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [1, 2, 3]\n",
- "myRDD= sc.parallelize(data)\n",
- "#map() returns [[1], [1, 2], [1, 2, 3]]\n",
- "mapRDD= myRDD.map(lambda x: range(1,x))\n",
- "#flatmap() returns [1, 1, 2, 1, 2, 3]\n",
- "flatMapRDD = myRDD.flatMap(lambda x: range(1,x))"
- ],
- "metadata": {
- "id": "0EQYOAEjKCka"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## filter()"
- ],
- "metadata": {
- "id": "EGkIstSWKHV_"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [1, 2, 3, 4, 5, 6]\n",
- "myRDD= sc.parallelize(data)\n",
- "#returns an RDD with only the elements that are divisible by 2\n",
- "newRDD= myRDD.filter(lambda x: x%2 == 0)\n",
- "print(newRDD.collect())"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "nsJ_5vZ4KIxm",
- "outputId": "7bbec148-e2b6-4730-ea3e-525f5e677301"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "[2, 4, 6]\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## distinct()"
- ],
- "metadata": {
- "id": "k66NCOyXKMGH"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [1, 2, 2, 3, 3, 3]\n",
- "myRDD= sc.parallelize(data)\n",
- "newRDD= myRDD.distinct()\n",
- "print(newRDD.collect())"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "segwXsP4KNjO",
- "outputId": "30491411-0585-47ab-d59d-758ba283d0a1"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "[2, 1, 3]\n"
- ]
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## groupByKey()"
- ],
- "metadata": {
- "id": "c4SOApzYKPC5"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "myRDD = sc.parallelize([('a', 1), ('a', 2), ('a', 3), ('b', 1)])\n",
- "#print result as list\n",
- "resultList= myRDD.groupByKey().mapValues(list)\n",
- "resultList.collect()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "N3-m37wMKQW1",
- "outputId": "c4a2d202-08e2-4d59-8668-f555208d7a8b"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[('b', [1]), ('a', [1, 2, 3])]"
- ]
- },
- "metadata": {},
- "execution_count": 16
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## reduceByKey()"
- ],
- "metadata": {
- "id": "-wwgB4nSKYVq"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "from operator import add\n",
- "myRDD = sc.parallelize([('a', 1), ('a', 2), ('a', 3), ('b', 1)])\n",
- "#adds the values by keys\n",
- "newRDD= myRDD.reduceByKey(add)\n",
- "newRDD.collect()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "nyGxP_ufKZ6y",
- "outputId": "e9dd5d08-1db5-4607-dfb0-1c9b88464c35"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[('b', 1), ('a', 6)]"
- ]
- },
- "metadata": {},
- "execution_count": 18
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## sortByKey()"
- ],
- "metadata": {
- "id": "4pJjGTUrKkAi"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "myRDD = sc.parallelize([('c', 1), ('d', 2), ('a', 3), ('b', 4)])\n",
- "#sort by key\n",
- "newRDD= myRDD.sortByKey()\n",
- "newRDD.collect()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "nya6PABeKldr",
- "outputId": "7e25d77a-786e-4d38-924b-3e159612c0a3"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[('a', 3), ('b', 4), ('c', 1), ('d', 2)]"
- ]
- },
- "metadata": {},
- "execution_count": 20
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## union()"
- ],
- "metadata": {
- "id": "qQiAF9EpKq3n"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "myRDD1 = sc.parallelize([1, 2, 3, 4])\n",
- "myRDD2 = sc.parallelize([ 3, 4, 5, 6, 7])\n",
- "#union of myRDD1 and myRDD2\n",
- "newRDD = myRDD1.union(myRDD2)\n",
- "newRDD.collect()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "LxfM314VKsnA",
- "outputId": "ea8067a2-07f3-47ed-9c74-8ed96b99d51f"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[1, 2, 3, 4, 3, 4, 5, 6, 7]"
- ]
- },
- "metadata": {},
- "execution_count": 21
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Actions PySpark"
- ],
- "metadata": {
- "id": "R5eqe2hPKugZ"
- }
- },
- {
- "cell_type": "markdown",
- "source": [
- "## count()"
- ],
- "metadata": {
- "id": "MZ_WZU1EKzVL"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= ['Scala', 'Python', 'Java', 'R']\n",
- "myRDD= sc.parallelize(data)\n",
- "#Returns 4 as output\n",
- "myRDD.count()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "PIXVbiyAKySe",
- "outputId": "c3ee0b44-b3cb-4712-84db-ab7835531916"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "4"
- ]
- },
- "metadata": {},
- "execution_count": 22
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## reduce()"
- ],
- "metadata": {
- "id": "Hv1Ha7gEK4x3"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [1, 2, 3, 4, 5]\n",
- "myRDD= sc.parallelize(data)\n",
- "#returns the product of all the elements\n",
- "myRDD.reduce(lambda x, y: x * y)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "01tur36zK6am",
- "outputId": "6eda15d5-ea2e-4dde-de45-c47c2a5ce2f4"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "120"
- ]
- },
- "metadata": {},
- "execution_count": 23
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "data= ['Scala', 'Python', 'Java', 'R']\n",
- "myRDD= sc.parallelize(data)\n",
- "#Concatenate the string elements\n",
- "myRDD.reduce( lambda x, y: x + y)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 36
- },
- "id": "O7jCKpFYK9XU",
- "outputId": "308babc8-4054-49d4-b004-579fc6f5c582"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "'ScalaPythonJavaR'"
- ],
- "application/vnd.google.colaboratory.intrinsic+json": {
- "type": "string"
- }
- },
- "metadata": {},
- "execution_count": 24
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## foreach()"
- ],
- "metadata": {
- "id": "QpULVIk4LBr6"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "def fun(x):\n",
- " print(x)\n",
- "data= ['Scala', 'Python', 'Java', 'R']\n",
- "myRDD= sc.parallelize(data)\n",
- "#function applied to all the elements\n",
- "myRDD.foreach(fun)"
- ],
- "metadata": {
- "id": "Gm7iAf0YLDnP"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "markdown",
- "source": [
- "## countByValue()"
- ],
- "metadata": {
- "id": "Yw6gTUqBLHF0"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= ['Python', 'Scala', 'Python', 'R', 'Python', 'Java', 'R']\n",
- "myRDD= sc.parallelize(data)\n",
- "#items() returns a list with all the dictionary keys and values returned by countByValue()\n",
- "myRDD.countByValue().items()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "u1ySKgxJLIRW",
- "outputId": "895bc41f-2500-4161-a9db-2e87609a833b"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "dict_items([('Python', 3), ('Scala', 1), ('R', 2), ('Java', 1)])"
- ]
- },
- "metadata": {},
- "execution_count": 27
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## countByKey()"
- ],
- "metadata": {
- "id": "9FhAg63XLcqr"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [('a', 1), ('b', 1), ('c', 1), ('a', 1)]\n",
- "myRDD = sc.parallelize(data)\n",
- "myRDD.countByKey().items()"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "DrLHUTGaLfSX",
- "outputId": "1ed0f052-5c7e-4f1b-8713-ddac4290bb99"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "dict_items([('a', 2), ('b', 1), ('c', 1)])"
- ]
- },
- "metadata": {},
- "execution_count": 28
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## take(n)"
- ],
- "metadata": {
- "id": "2PI_T0PnLlVL"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [2, 5, 3, 8, 4]\n",
- "myRDD= sc.parallelize(data)\n",
- "#return the first 2 elements\n",
- "myRDD.take(3)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "z2jLc1B5LmzG",
- "outputId": "aff87ab8-8e86-44c0-ead1-ac936b11e43f"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[2, 5, 3]"
- ]
- },
- "metadata": {},
- "execution_count": 29
- }
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "## top(n)"
- ],
- "metadata": {
- "id": "9ZHLsm5YLqCK"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "data= [2, 5, 3, 8, 4]\n",
- "myRDD= sc.parallelize(data)\n",
- "#return the first 2 elements\n",
- "myRDD.take(3)"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "TNZCb9sOLrLG",
- "outputId": "0a1b929d-637d-40a9-a6ac-b62696e3cf91"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "[2, 5, 3]"
- ]
- },
- "metadata": {},
- "execution_count": 30
- }
- ]
- }
- ]
-}
\ No newline at end of file
diff --git a/cereal.csv b/cereal.csv
deleted file mode 100644
index 43dc0a3..0000000
--- a/cereal.csv
+++ /dev/null
@@ -1,78 +0,0 @@
-name,mfr,type,calories,protein,fat,sodium,fiber,carbo,sugars,potass,vitamins,shelf,weight,cups,rating
-100% Bran,N,C,70,4,1,130,10,5,6,280,25,3,1,0.33,68.402973
-100% Natural Bran,Q,C,120,3,5,15,2,8,8,135,0,3,1,1,33.983679
-All-Bran,K,C,70,4,1,260,9,7,5,320,25,3,1,0.33,59.425505
-All-Bran with Extra Fiber,K,C,50,4,0,140,14,8,0,330,25,3,1,0.5,93.704912
-Almond Delight,R,C,110,2,2,200,1,14,8,-1,25,3,1,0.75,34.384843
-Apple Cinnamon Cheerios,G,C,110,2,2,180,1.5,10.5,10,70,25,1,1,0.75,29.509541
-Apple Jacks,K,C,110,2,0,125,1,11,14,30,25,2,1,1,33.174094
-Basic 4,G,C,130,3,2,210,2,18,8,100,25,3,1.33,0.75,37.038562
-Bran Chex,R,C,90,2,1,200,4,15,6,125,25,1,1,0.67,49.120253
-Bran Flakes,P,C,90,3,0,210,5,13,5,190,25,3,1,0.67,53.313813
-Cap'n'Crunch,Q,C,120,1,2,220,0,12,12,35,25,2,1,0.75,18.042851
-Cheerios,G,C,110,6,2,290,2,17,1,105,25,1,1,1.25,50.764999
-Cinnamon Toast Crunch,G,C,120,1,3,210,0,13,9,45,25,2,1,0.75,19.823573
-Clusters,G,C,110,3,2,140,2,13,7,105,25,3,1,0.5,40.400208
-Cocoa Puffs,G,C,110,1,1,180,0,12,13,55,25,2,1,1,22.736446
-Corn Chex,R,C,110,2,0,280,0,22,3,25,25,1,1,1,41.445019
-Corn Flakes,K,C,100,2,0,290,1,21,2,35,25,1,1,1,45.863324
-Corn Pops,K,C,110,1,0,90,1,13,12,20,25,2,1,1,35.782791
-Count Chocula,G,C,110,1,1,180,0,12,13,65,25,2,1,1,22.396513
-Cracklin' Oat Bran,K,C,110,3,3,140,4,10,7,160,25,3,1,0.5,40.448772
-Cream of Wheat (Quick),N,H,100,3,0,80,1,21,0,-1,0,2,1,1,64.533816
-Crispix,K,C,110,2,0,220,1,21,3,30,25,3,1,1,46.895644
-Crispy Wheat & Raisins,G,C,100,2,1,140,2,11,10,120,25,3,1,0.75,36.176196
-Double Chex,R,C,100,2,0,190,1,18,5,80,25,3,1,0.75,44.330856
-Froot Loops,K,C,110,2,1,125,1,11,13,30,25,2,1,1,32.207582
-Frosted Flakes,K,C,110,1,0,200,1,14,11,25,25,1,1,0.75,31.435973
-Frosted Mini-Wheats,K,C,100,3,0,0,3,14,7,100,25,2,1,0.8,58.345141
-Fruit & Fibre Dates; Walnuts; and Oats,P,C,120,3,2,160,5,12,10,200,25,3,1.25,0.67,40.917047
-Fruitful Bran,K,C,120,3,0,240,5,14,12,190,25,3,1.33,0.67,41.015492
-Fruity Pebbles,P,C,110,1,1,135,0,13,12,25,25,2,1,0.75,28.025765
-Golden Crisp,P,C,100,2,0,45,0,11,15,40,25,1,1,0.88,35.252444
-Golden Grahams,G,C,110,1,1,280,0,15,9,45,25,2,1,0.75,23.804043
-Grape Nuts Flakes,P,C,100,3,1,140,3,15,5,85,25,3,1,0.88,52.076897
-Grape-Nuts,P,C,110,3,0,170,3,17,3,90,25,3,1,0.25,53.371007
-Great Grains Pecan,P,C,120,3,3,75,3,13,4,100,25,3,1,0.33,45.811716
-Honey Graham Ohs,Q,C,120,1,2,220,1,12,11,45,25,2,1,1,21.871292
-Honey Nut Cheerios,G,C,110,3,1,250,1.5,11.5,10,90,25,1,1,0.75,31.072217
-Honey-comb,P,C,110,1,0,180,0,14,11,35,25,1,1,1.33,28.742414
-Just Right Crunchy Nuggets,K,C,110,2,1,170,1,17,6,60,100,3,1,1,36.523683
-Just Right Fruit & Nut,K,C,140,3,1,170,2,20,9,95,100,3,1.3,0.75,36.471512
-Kix,G,C,110,2,1,260,0,21,3,40,25,2,1,1.5,39.241114
-Life,Q,C,100,4,2,150,2,12,6,95,25,2,1,0.67,45.328074
-Lucky Charms,G,C,110,2,1,180,0,12,12,55,25,2,1,1,26.734515
-Maypo,A,H,100,4,1,0,0,16,3,95,25,2,1,1,54.850917
-Muesli Raisins; Dates; & Almonds,R,C,150,4,3,95,3,16,11,170,25,3,1,1,37.136863
-Muesli Raisins; Peaches; & Pecans,R,C,150,4,3,150,3,16,11,170,25,3,1,1,34.139765
-Mueslix Crispy Blend,K,C,160,3,2,150,3,17,13,160,25,3,1.5,0.67,30.313351
-Multi-Grain Cheerios,G,C,100,2,1,220,2,15,6,90,25,1,1,1,40.105965
-Nut&Honey Crunch,K,C,120,2,1,190,0,15,9,40,25,2,1,0.67,29.924285
-Nutri-Grain Almond-Raisin,K,C,140,3,2,220,3,21,7,130,25,3,1.33,0.67,40.692320
-Nutri-grain Wheat,K,C,90,3,0,170,3,18,2,90,25,3,1,1,59.642837
-Oatmeal Raisin Crisp,G,C,130,3,2,170,1.5,13.5,10,120,25,3,1.25,0.5,30.450843
-Post Nat. Raisin Bran,P,C,120,3,1,200,6,11,14,260,25,3,1.33,0.67,37.840594
-Product 19,K,C,100,3,0,320,1,20,3,45,100,3,1,1,41.503540
-Puffed Rice,Q,C,50,1,0,0,0,13,0,15,0,3,0.5,1,60.756112
-Puffed Wheat,Q,C,50,2,0,0,1,10,0,50,0,3,0.5,1,63.005645
-Quaker Oat Squares,Q,C,100,4,1,135,2,14,6,110,25,3,1,0.5,49.511874
-Quaker Oatmeal,Q,H,100,5,2,0,2.7,-1,-1,110,0,1,1,0.67,50.828392
-Raisin Bran,K,C,120,3,1,210,5,14,12,240,25,2,1.33,0.75,39.259197
-Raisin Nut Bran,G,C,100,3,2,140,2.5,10.5,8,140,25,3,1,0.5,39.703400
-Raisin Squares,K,C,90,2,0,0,2,15,6,110,25,3,1,0.5,55.333142
-Rice Chex,R,C,110,1,0,240,0,23,2,30,25,1,1,1.13,41.998933
-Rice Krispies,K,C,110,2,0,290,0,22,3,35,25,1,1,1,40.560159
-Shredded Wheat,N,C,80,2,0,0,3,16,0,95,0,1,0.83,1,68.235885
-Shredded Wheat 'n'Bran,N,C,90,3,0,0,4,19,0,140,0,1,1,0.67,74.472949
-Shredded Wheat spoon size,N,C,90,3,0,0,3,20,0,120,0,1,1,0.67,72.801787
-Smacks,K,C,110,2,1,70,1,9,15,40,25,2,1,0.75,31.230054
-Special K,K,C,110,6,0,230,1,16,3,55,25,1,1,1,53.131324
-Strawberry Fruit Wheats,N,C,90,2,0,15,3,15,5,90,25,2,1,1,59.363993
-Total Corn Flakes,G,C,110,2,1,200,0,21,3,35,100,3,1,1,38.839746
-Total Raisin Bran,G,C,140,3,1,190,4,15,14,230,100,3,1.5,1,28.592785
-Total Whole Grain,G,C,100,3,1,200,3,16,3,110,100,3,1,1,46.658844
-Triples,G,C,110,2,1,250,0,21,3,60,25,3,1,0.75,39.106174
-Trix,G,C,110,1,1,140,0,13,12,25,25,2,1,1,27.753301
-Wheat Chex,R,C,100,3,1,230,3,17,3,115,25,1,1,0.67,49.787445
-Wheaties,G,C,100,3,1,200,3,17,3,110,25,1,1,1,51.592193
-Wheaties Honey Gold,G,C,110,2,1,200,1,16,8,60,25,1,1,0.75,36.187559