![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "_sfWZU_eST2O"
+ },
+ "source": [
+ "**NOTE: ALL THE COMMANDS FOR PLOTTING A FIGURE SHOULD ALL GO IN THE SAME CELL. SEPARATING THEM OUT INTO MULTIPLE CELLS MAY CAUSE NOTHING TO SHOW UP.**\n",
+ "\n",
+ "# Exercises\n",
+ "\n",
+ "Follow the instructions to recreate the plots using this data:\n",
+ "\n",
+ "## Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "l0eZ10dLST2X"
+ },
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "x = np.arange(0,100)\n",
+ "y = x*2\n",
+ "z = x**2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "veY4-lsGST2c"
+ },
+ "source": [
+ "**Import matplotlib.pyplot as plt**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "tAOmEcNKST2e"
+ },
+ "outputs": [],
+ "source": [
+ "import matplotlib.pyplot as plt"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "5j_39gsVST2f"
+ },
+ "source": [
+ "## Exercise 1\n",
+ "\n",
+ "**Follow along with these steps**\n",
+ "* Create a figure object called fig using plt.figure()\n",
+ "* Use add_axes to add an axis to the figure canvas at [0,0,1,1]. Call this new axis ax.\n",
+ "* Plot (x,y) on that axes and set the labels and titles to match the plot below:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "03Ts4r5SST2g",
+ "outputId": "d1d85a91-d458-4748-a276-06fb79c06159",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 599
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "Text(0.5, 1.0, 'title')"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 7
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "HfJB9JnS9xlK"
+ },
+ "source": [
+ "# NumPy Exercises\n",
+ "\n",
+ "Now that we've learned about NumPy let's test your knowledge. We'll start off with a few simple tasks, and then you'll be asked some more complicated questions."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "u9POEVg29xlM"
+ },
+ "source": [
+ "#### Import NumPy as np"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "yyS-PuO_9xlM"
+ },
+ "outputs": [],
+ "source": [
+ "import numpy as np"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ehlpKUPc9xlM"
+ },
+ "source": [
+ "#### Create an array of 10 zeros"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "aEQkK-Dw9xlN"
+ },
+ "outputs": [],
+ "source": [
+ "arr = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "6QHp05Ei9xlN"
+ },
+ "source": [
+ "#### Create an array of 10 ones"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "scrolled": true,
+ "id": "ebe9xrC29xlN"
+ },
+ "outputs": [],
+ "source": [
+ "arr=np.full(10,1)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ziS-l3xp9xlO"
+ },
+ "source": [
+ "#### Create an array of 10 fives"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "fFC7bqLM9xlO",
+ "outputId": "119c96dc-0306-4ccf-fe06-9ffa456a0436"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([5., 5., 5., 5., 5., 5., 5., 5., 5., 5.])"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr = np.full(10, 5)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "kBugMXlC9xlO"
+ },
+ "source": [
+ "#### Create an array of the integers from 10 to 50"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "JsO6qS9R9xlO",
+ "outputId": "20239a7d-38ca-4f39-f01d-4be944c72b1b"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26,\n",
+ " 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,\n",
+ " 44, 45, 46, 47, 48, 49, 50])"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.arange(10,51)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "dMw4V2L79xlO"
+ },
+ "source": [
+ "#### Create an array of all the even integers from 10 to 50"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "4lK-5SQV9xlO",
+ "outputId": "2e053b90-8713-42fa-9739-ee16b9ccd102"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38, 40, 42,\n",
+ " 44, 46, 48, 50])"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.arange(10,51,2)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "g__F0rB39xlP"
+ },
+ "source": [
+ "#### Create a 3x3 matrix with values ranging from 0 to 8"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "MmVXCn0K9xlP",
+ "outputId": "6056283e-4ee4-494f-b83c-f19596df9af8"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[0, 1, 2],\n",
+ " [3, 4, 5],\n",
+ " [6, 7, 8]])"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.arange(0,9)\n",
+ "np.reshape(arr,(3,3))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "4YfT0aLo9xlP"
+ },
+ "source": [
+ "#### Create a 3x3 identity matrix"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "UHa42UpQ9xlP",
+ "outputId": "ac24486e-3249-41f3-e6ca-49b88c6a2125"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[1., 0., 0.],\n",
+ " [0., 1., 0.],\n",
+ " [0., 0., 1.]])"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.identity(3)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "bfwDbjhI9xlP"
+ },
+ "source": [
+ "#### Use NumPy to generate a random number between 0 and 1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Z0OroZxW9xlP",
+ "outputId": "0955e089-091a-4a57-ed5c-653df5d5a56c"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([0.62390023])"
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.random.rand(1)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "rLW0Jjzp9xlP"
+ },
+ "source": [
+ "#### Use NumPy to generate an array of 25 random numbers sampled from a standard normal distribution"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "szluy14n9xlP",
+ "outputId": "176f3078-97b7-4a7d-e885-5a1224b13fec"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([-0.11617859, -0.13631661, 0.7150532 , -0.27734985, 0.06538679,\n",
+ " -1.16994467, -1.45669789, 1.56838663, 1.13525628, -0.69958045,\n",
+ " 0.06961791, -0.07441215, 0.99718638, 0.28416225, -0.14591454,\n",
+ " 0.02658355, -2.05644532, 0.66783981, 2.57474944, 1.3365862 ,\n",
+ " -0.35696454, -1.57424745, 0.76840978, -0.79557035, 0.91504545])"
+ ]
+ },
+ "execution_count": 34,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.random.randn(25)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "_GhI8LYn9xlP"
+ },
+ "source": [
+ "#### Create the following matrix:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "wS1ZBddV9xlP",
+ "outputId": "92588415-77b9-49c7-cfdd-9b67602a3386"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[0.01, 0.02, 0.03, 0.04, 0.05, 0.06, 0.07, 0.08, 0.09, 0.1 ],\n",
+ " [0.11, 0.12, 0.13, 0.14, 0.15, 0.16, 0.17, 0.18, 0.19, 0.2 ],\n",
+ " [0.21, 0.22, 0.23, 0.24, 0.25, 0.26, 0.27, 0.28, 0.29, 0.3 ],\n",
+ " [0.31, 0.32, 0.33, 0.34, 0.35, 0.36, 0.37, 0.38, 0.39, 0.4 ],\n",
+ " [0.41, 0.42, 0.43, 0.44, 0.45, 0.46, 0.47, 0.48, 0.49, 0.5 ],\n",
+ " [0.51, 0.52, 0.53, 0.54, 0.55, 0.56, 0.57, 0.58, 0.59, 0.6 ],\n",
+ " [0.61, 0.62, 0.63, 0.64, 0.65, 0.66, 0.67, 0.68, 0.69, 0.7 ],\n",
+ " [0.71, 0.72, 0.73, 0.74, 0.75, 0.76, 0.77, 0.78, 0.79, 0.8 ],\n",
+ " [0.81, 0.82, 0.83, 0.84, 0.85, 0.86, 0.87, 0.88, 0.89, 0.9 ],\n",
+ " [0.91, 0.92, 0.93, 0.94, 0.95, 0.96, 0.97, 0.98, 0.99, 1. ]])"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.arange(0.01,1.01,0.01)\n",
+ "np.reshape(arr,(10,10))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "3OqA-QtL9xlQ"
+ },
+ "source": [
+ "#### Create an array of 20 linearly spaced points between 0 and 1:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "FNXTugQ29xlQ",
+ "outputId": "674dbbff-9a87-4463-933f-07b2bbd15ce2"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([0. , 0.05263158, 0.10526316, 0.15789474, 0.21052632,\n",
+ " 0.26315789, 0.31578947, 0.36842105, 0.42105263, 0.47368421,\n",
+ " 0.52631579, 0.57894737, 0.63157895, 0.68421053, 0.73684211,\n",
+ " 0.78947368, 0.84210526, 0.89473684, 0.94736842, 1. ])"
+ ]
+ },
+ "execution_count": 41,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr=np.linspace(0,1,20)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "elx0EaxE9xlQ"
+ },
+ "source": [
+ "## Numpy Indexing and Selection\n",
+ "\n",
+ "Now you will be given a few matrices, and be asked to replicate the resulting matrix outputs:"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "2Tbm9kVf9xlQ"
+ },
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "Ft8P8e249xlQ",
+ "outputId": "6fdc9496-50f6-436f-bbef-7bb7e91e4e05",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "[[ 1 2 3 4 5]\n",
+ " [ 6 7 8 9 10]\n",
+ " [11 12 13 14 15]\n",
+ " [16 17 18 19 20]\n",
+ " [21 22 23 24 25]]\n"
+ ]
+ }
+ ],
+ "source": [
+ "arr=np.arange(1,26)\n",
+ "arr1=np.reshape(arr,(5,5))\n",
+ "print(arr1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "WrcFkpGL9xlQ",
+ "outputId": "aeec25dd-28fc-4993-fbde-663c4508cf07",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "array([[11, 12, 13, 14, 15],\n",
+ " [16, 17, 18, 19, 20],\n",
+ " [21, 22, 23, 24, 25]])"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 7
+ }
+ ],
+ "source": [
+ "arr1[2:5, 0:5]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "rnUSntEa9xlQ",
+ "outputId": "34a17749-8d5c-4534-eda2-8e6ebd154922",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "np.int64(20)"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 9
+ }
+ ],
+ "source": [
+ "arr1[3,-1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "3DMBC_wp9xlQ",
+ "outputId": "03a36471-377d-4441-d39f-68b528de64b2",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "array([[ 2],\n",
+ " [ 7],\n",
+ " [12]])"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 10
+ }
+ ],
+ "source": [
+ "arr1[0:3,1:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "pGjD4HUK9xlQ",
+ "outputId": "d9eadd5a-ac80-4598-bfa5-bb84966bb8e5",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "array([[21, 22, 23, 24, 25]])"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 11
+ }
+ ],
+ "source": [
+ "arr1[4:5, 0:5]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "dqsdpxUo9xlR",
+ "outputId": "9dc2f228-6527-461f-8ab8-ea578fbf8bb1",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "array([[16, 17, 18, 19, 20],\n",
+ " [21, 22, 23, 24, 25]])"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 12
+ }
+ ],
+ "source": [
+ "arr1[3:5, 0:5]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "collapsed": true,
+ "id": "6vtHuVJU9xlf"
+ },
+ "source": [
+ "# Great Job!"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.12"
+ },
+ "colab": {
+ "provenance": [],
+ "include_colab_link": true
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
\ No newline at end of file
diff --git a/Assignment 1/Assignment1_Utpal/Utpal_Pandas_Assignment.ipynb b/Assignment 1/Assignment1_Utpal/Utpal_Pandas_Assignment.ipynb
new file mode 100644
index 00000000..2f20e59c
--- /dev/null
+++ b/Assignment 1/Assignment1_Utpal/Utpal_Pandas_Assignment.ipynb
@@ -0,0 +1,1829 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "view-in-github",
+ "colab_type": "text"
+ },
+ "source": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## General Instructions for all Assignments"
+ ],
+ "metadata": {
+ "id": "AWDeauE3Bdzs"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "1. Fork the repository and make a copy of this notebook and rename it as your name_Assignment1_Pandas\n",
+ "2. Generate a pull request. The pull request message should also be yourname_Assignment1"
+ ],
+ "metadata": {
+ "id": "Xaf9uMvXBJEC"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "\n",
+ "1. This code notebook is composed of cells. Each cell is either text or Python code.\n",
+ "2. To run a cell of code, click the \"play button\" icon to the left of the cell or click on the cell and press \"Shift+Enter\" on your keyboard. This will execute the Python code contained in the cell. Executing a cell that defines a variable is important before executing or authoring a cell that depends on that previously created variable assignment.\n"
+ ],
+ "metadata": {
+ "id": "4_6uxHVGB_XT"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [],
+ "metadata": {
+ "id": "b68xNjkKCBIF"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "BiD4gl6_cAYs"
+ },
+ "outputs": [],
+ "source": [
+ "#import pandas library\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "JUtm9KricAYu"
+ },
+ "outputs": [],
+ "source": [
+ "df = pd.read_csv('/content/Iris.csv') #enter path for the Iris csv in the brackets\n",
+ "#reads the csv file and stores it in a data frame(define in the pandas library)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "qzUnSkfRcAYu"
+ },
+ "outputs": [],
+ "source": [
+ "dictionary = {'col':[4,2,3], 'col2':[4,7,6], 'col3':[7,10,9]}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "ACswu4BXcAYu"
+ },
+ "outputs": [],
+ "source": [
+ "dictionarydf = pd.DataFrame.from_dict(dictionary)\n",
+ "#it creats a new datafram which stores the dictionary made above"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df.head()\n",
+ "#shows top 5 rows (row indexing starts from 0)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 206
+ },
+ "id": "MvYNz8E2dp3K",
+ "outputId": "366bc39c-7df6-4cc7-ae60-03aedd2571f4"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species\n",
+ "0 1 5.1 3.5 1.4 0.2 Iris-setosa\n",
+ "1 2 4.9 3.0 1.4 0.2 Iris-setosa\n",
+ "2 3 4.7 3.2 1.3 0.2 Iris-setosa\n",
+ "3 4 4.6 3.1 1.5 0.2 Iris-setosa\n",
+ "4 5 5.0 3.6 1.4 0.2 Iris-setosa"
+ ],
+ "text/html": [
+ "\n",
+ " | \n", + " | Id | \n", + "SepalLengthCm | \n", + "SepalWidthCm | \n", + "PetalLengthCm | \n", + "PetalWidthCm | \n", + "Species | \n", + "
|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "5.1 | \n", + "3.5 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 1 | \n", + "2 | \n", + "4.9 | \n", + "3.0 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 2 | \n", + "3 | \n", + "4.7 | \n", + "3.2 | \n", + "1.3 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 3 | \n", + "4 | \n", + "4.6 | \n", + "3.1 | \n", + "1.5 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 4 | \n", + "5 | \n", + "5.0 | \n", + "3.6 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| \n", + " | SepalLengthCm | \n", + "SepalWidthCm | \n", + "
|---|---|---|
| 0 | \n", + "5.1 | \n", + "3.5 | \n", + "
| 1 | \n", + "4.9 | \n", + "3.0 | \n", + "
| 2 | \n", + "4.7 | \n", + "3.2 | \n", + "
| 3 | \n", + "4.6 | \n", + "3.1 | \n", + "
| 4 | \n", + "5.0 | \n", + "3.6 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "
| 145 | \n", + "6.7 | \n", + "3.0 | \n", + "
| 146 | \n", + "6.3 | \n", + "2.5 | \n", + "
| 147 | \n", + "6.5 | \n", + "3.0 | \n", + "
| 148 | \n", + "6.2 | \n", + "3.4 | \n", + "
| 149 | \n", + "5.9 | \n", + "3.0 | \n", + "
150 rows × 2 columns
\n", + "| \n", + " | Id | \n", + "SepalLengthCm | \n", + "SepalWidthCm | \n", + "PetalLengthCm | \n", + "PetalWidthCm | \n", + "Species | \n", + "
|---|---|---|---|---|---|---|
| 22 | \n", + "23 | \n", + "4.6 | \n", + "3.6 | \n", + "1.0 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 23 | \n", + "24 | \n", + "5.1 | \n", + "3.3 | \n", + "1.7 | \n", + "0.5 | \n", + "Iris-setosa | \n", + "
| 24 | \n", + "25 | \n", + "4.8 | \n", + "3.4 | \n", + "1.9 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 25 | \n", + "26 | \n", + "5.0 | \n", + "3.0 | \n", + "1.6 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 26 | \n", + "27 | \n", + "5.0 | \n", + "3.4 | \n", + "1.6 | \n", + "0.4 | \n", + "Iris-setosa | \n", + "
| 27 | \n", + "28 | \n", + "5.2 | \n", + "3.5 | \n", + "1.5 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 28 | \n", + "29 | \n", + "5.2 | \n", + "3.4 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 29 | \n", + "30 | \n", + "4.7 | \n", + "3.2 | \n", + "1.6 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 30 | \n", + "31 | \n", + "4.8 | \n", + "3.1 | \n", + "1.6 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 31 | \n", + "32 | \n", + "5.4 | \n", + "3.4 | \n", + "1.5 | \n", + "0.4 | \n", + "Iris-setosa | \n", + "
| 32 | \n", + "33 | \n", + "5.2 | \n", + "4.1 | \n", + "1.5 | \n", + "0.1 | \n", + "Iris-setosa | \n", + "
| \n", + " | Id | \n", + "SepalLengthCm | \n", + "SepalWidthCm | \n", + "PetalLengthCm | \n", + "PetalWidthCm | \n", + "Species | \n", + "
|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "5.1 | \n", + "3.5 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 1 | \n", + "2 | \n", + "4.9 | \n", + "3.0 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 2 | \n", + "3 | \n", + "4.7 | \n", + "3.2 | \n", + "1.3 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 3 | \n", + "4 | \n", + "4.6 | \n", + "3.1 | \n", + "1.5 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| 4 | \n", + "5 | \n", + "5.0 | \n", + "3.6 | \n", + "1.4 | \n", + "0.2 | \n", + "Iris-setosa | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 145 | \n", + "146 | \n", + "6.7 | \n", + "3.0 | \n", + "5.2 | \n", + "2.3 | \n", + "Iris-virginica | \n", + "
| 146 | \n", + "147 | \n", + "6.3 | \n", + "2.5 | \n", + "5.0 | \n", + "1.9 | \n", + "Iris-virginica | \n", + "
| 147 | \n", + "148 | \n", + "6.5 | \n", + "3.0 | \n", + "5.2 | \n", + "2.0 | \n", + "Iris-virginica | \n", + "
| 148 | \n", + "149 | \n", + "6.2 | \n", + "3.4 | \n", + "5.4 | \n", + "2.3 | \n", + "Iris-virginica | \n", + "
| 149 | \n", + "150 | \n", + "5.9 | \n", + "3.0 | \n", + "5.1 | \n", + "1.8 | \n", + "Iris-virginica | \n", + "
150 rows × 6 columns
\n", + "| \n", + " | 0 | \n", + "
|---|---|
| Id | \n", + "0 | \n", + "
| SepalLengthCm | \n", + "0 | \n", + "
| SepalWidthCm | \n", + "0 | \n", + "
| PetalLengthCm | \n", + "0 | \n", + "
| PetalWidthCm | \n", + "0 | \n", + "
| Species | \n", + "0 | \n", + "
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true,
+ "id": "25VUFl3B_qRd"
+ },
+ "outputs": [],
+ "source": [
+ "import yfinance as yf\n",
+ "import plotly.graph_objects as go\n",
+ "from plotly.subplots import make_subplots"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "ticker_symbol = \"AAPL\"\n",
+ "import datetime\n",
+ "end_date = datetime.date.today()\n",
+ "start_date = end_date - datetime.timedelta(days=6*30)\n",
+ "df = yf.download(ticker_symbol, start=start_date, end=end_date, interval='1d')\n",
+ "df.columns=df.columns.get_level_values(0)\n",
+ "\n",
+ "display(df.head())"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 329
+ },
+ "id": "mWnVmE718i3b",
+ "outputId": "dfd88a50-b6c2-4fec-dec9-edcac624be2f"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "/tmp/ipython-input-496795122.py:5: FutureWarning:\n",
+ "\n",
+ "YF.download() has changed argument auto_adjust default to True\n",
+ "\n",
+ "[*********************100%***********************] 1 of 1 completed\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Price Close High Low Open Volume\n",
+ "Date \n",
+ "2025-06-20 200.577698 201.276224 196.446397 197.823502 96813500\n",
+ "2025-06-23 201.076660 201.874982 198.542003 201.206392 55814300\n",
+ "2025-06-24 199.879181 203.012583 199.779385 202.164363 54064000\n",
+ "2025-06-25 201.136536 203.242103 200.198508 201.026766 39525700\n",
+ "2025-06-26 200.577698 202.214251 199.040940 201.006787 50799100"
+ ],
+ "text/html": [
+ "\n",
+ " | Price | \n", + "Close | \n", + "High | \n", + "Low | \n", + "Open | \n", + "Volume | \n", + "
|---|---|---|---|---|---|
| Date | \n", + "\n", + " | \n", + " | \n", + " | \n", + " | \n", + " |
| 2025-06-20 | \n", + "200.577698 | \n", + "201.276224 | \n", + "196.446397 | \n", + "197.823502 | \n", + "96813500 | \n", + "
| 2025-06-23 | \n", + "201.076660 | \n", + "201.874982 | \n", + "198.542003 | \n", + "201.206392 | \n", + "55814300 | \n", + "
| 2025-06-24 | \n", + "199.879181 | \n", + "203.012583 | \n", + "199.779385 | \n", + "202.164363 | \n", + "54064000 | \n", + "
| 2025-06-25 | \n", + "201.136536 | \n", + "203.242103 | \n", + "200.198508 | \n", + "201.026766 | \n", + "39525700 | \n", + "
| 2025-06-26 | \n", + "200.577698 | \n", + "202.214251 | \n", + "199.040940 | \n", + "201.006787 | \n", + "50799100 | \n", + "
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "id": "bSWgTS-AMcqo"
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+ "from sklearn.compose import ColumnTransformer\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.neural_network import MLPClassifier\n",
+ "from sklearn.metrics import (\n",
+ " accuracy_score,\n",
+ " precision_score,\n",
+ " recall_score,\n",
+ " f1_score,\n",
+ " confusion_matrix\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df=pd.read_csv(\"/content/quantvision_financial_dataset_200.csv\")\n",
+ "df.head()\n",
+ "X=df.drop(\"future_trend\",axis=1)\n",
+ "Y=df[\"future_trend\"]\n",
+ "cat_features=[\"asset_type\",\"market_regime\"]"
+ ],
+ "metadata": {
+ "id": "AZ4XbbR4Pzzp"
+ },
+ "execution_count": 5,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "num_features=[\n",
+ " \"lookback_days\",\n",
+ " \"high_volatility\",\n",
+ " \"trend_continuation\",\n",
+ " \"technical_score\",\n",
+ " \"edge_density\",\n",
+ " \"slope_strength\",\n",
+ " \"candlestick_variance\",\n",
+ " \"pattern_symmetry\"\n",
+ "]"
+ ],
+ "metadata": {
+ "id": "bwPBoRWWQ8qZ"
+ },
+ "execution_count": 6,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "preprocessing=ColumnTransformer(\n",
+ " transformers=[\n",
+ " (\"num\", StandardScaler(), num_features),\n",
+ " (\"cat\", OneHotEncoder(drop=\"first\"), cat_features)\n",
+ " ]\n",
+ ")"
+ ],
+ "metadata": {
+ "id": "tmR6X8oSRBj6"
+ },
+ "execution_count": 7,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "X_train,X_test,Y_train,Y_test=train_test_split(\n",
+ " X,\n",
+ " Y,\n",
+ " test_size=0.33,\n",
+ " random_state=7,\n",
+ " stratify=Y\n",
+ ")"
+ ],
+ "metadata": {
+ "id": "RX2503LYRGcr"
+ },
+ "execution_count": 13,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "log_model=Pipeline(steps=[\n",
+ " (\"preprocessor\", preprocessing),\n",
+ " (\"classifier\", LogisticRegression(random_state=7, max_iter=500))\n",
+ "])\n",
+ "log_model.fit(X_train,Y_train)\n",
+ "Y_pred_log=log_model.predict(X_test)\n",
+ "print(\"logistic_reg model Performance:\")\n",
+ "print(\"accuracy:\", accuracy_score(Y_test, Y_pred_log))\n",
+ "print(\"precision:\", precision_score(Y_test, Y_pred_log))\n",
+ "print(\"recall:\", recall_score(Y_test, Y_pred_log))\n",
+ "print(\"f1 score:\", f1_score(Y_test, Y_pred_log))\n",
+ "print(\"confusion matrix:\\n\", confusion_matrix(Y_test, Y_pred_log))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "vGJ1Vn7iRZg6",
+ "outputId": "93c0aaea-8201-4f31-afed-34daa85977cb"
+ },
+ "execution_count": 14,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "logistic_reg model Performance:\n",
+ "accuracy: 0.9393939393939394\n",
+ "precision: 0.953125\n",
+ "recall: 0.9838709677419355\n",
+ "f1 score: 0.9682539682539683\n",
+ "confusion matrix:\n",
+ " [[ 1 3]\n",
+ " [ 1 61]]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "nn_model=Pipeline(steps=[\n",
+ " (\"preprocessor\", preprocessing),\n",
+ " (\"classifier\", MLPClassifier(\n",
+ " hidden_layer_sizes=(64, 32),\n",
+ " activation=\"relu\",\n",
+ " solver=\"adam\",\n",
+ " max_iter=500,\n",
+ " random_state=7\n",
+ " ))\n",
+ "])\n",
+ "nn_model.fit(X_train, Y_train)\n",
+ "Y_pred_nn=nn_model.predict(X_test)\n",
+ "print(\"\")\n",
+ "print(\"neural_network model Performance:\")\n",
+ "print(\"accuracy:\", accuracy_score(Y_test, Y_pred_nn))\n",
+ "print(\"precision:\", precision_score(Y_test, Y_pred_nn))\n",
+ "print(\"recall:\", recall_score(Y_test, Y_pred_nn))\n",
+ "print(\"f1 score:\", f1_score(Y_test, Y_pred_nn))\n",
+ "print(\"confusion matrix:\\n\", confusion_matrix(Y_test, Y_pred_nn))\n",
+ "print(\"\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "sJrfxJGlRrnO",
+ "outputId": "d1da8404-3408-44db-f524-166d01c885a8"
+ },
+ "execution_count": 15,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "\n",
+ "neural_network model Performance:\n",
+ "accuracy: 0.9545454545454546\n",
+ "precision: 0.9836065573770492\n",
+ "recall: 0.967741935483871\n",
+ "f1 score: 0.975609756097561\n",
+ "confusion matrix:\n",
+ " [[ 3 1]\n",
+ " [ 2 60]]\n",
+ "\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "finaldata =pd.DataFrame({\n",
+ " \"model\": [\"logmodel\", \"nn_model\"],\n",
+ " \"accuracy\": [accuracy_score(Y_test, Y_pred_log), accuracy_score(Y_test, Y_pred_nn)],\n",
+ " \"precision\": [precision_score(Y_test, Y_pred_log), precision_score(Y_test, Y_pred_nn)],\n",
+ " \"recall\": [recall_score(Y_test, Y_pred_log), recall_score(Y_test, Y_pred_nn)],\n",
+ " \"f1_score\": [f1_score(Y_test, Y_pred_log), f1_score(Y_test, Y_pred_nn)]\n",
+ "})\n",
+ "print(finaldata)\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "Sloq0SQSSWGP",
+ "outputId": "c52d9623-ac7e-4006-bce2-fd207047c421"
+ },
+ "execution_count": 16,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ " model accuracy precision recall f1_score\n",
+ "0 logmodel 0.939394 0.953125 0.983871 0.968254\n",
+ "1 nn_model 0.954545 0.983607 0.967742 0.975610\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "We prioritize the F1-score for evaluation since it provides a balanced evaluation.\n",
+ "AS NN_model has better F1-score we say that:\n",
+ "\n",
+ " **\"NN MODEL WINS\"**"
+ ],
+ "metadata": {
+ "id": "e2mLkYkuCrlH"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Logistic Regression works okay when the market is calm and follows linear trends, but it struggles when things get complicated or change suddenly. Neural Networks do better because they can learn more complex patterns and adapt when market behavior shifts.\n",
+ "\n",
+ "That said, no model can predict the market perfectly. Big news, sudden crashes, or extreme volatility can confuse even the best model. This is why predictions should always be used carefully, along with good risk management and practical market understanding\n",
+ "\n"
+ ],
+ "metadata": {
+ "id": "tS84XBdc_ykS"
+ }
+ }
+ ]
+}
\ No newline at end of file