Skip to content

zawarkhan_KHI_MongoDB #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

zawarkhan_KHI_MongoDB #3

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3154ff0
Add files via upload
May 12, 2017
f44fd62
Add files via upload
May 12, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
334 changes: 334 additions & 0 deletions ZawarKhan_khi_MongoDB.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,334 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
" import pandas as pd\n",
"import numpy as np\n",
"import json\n",
"import csv\n",
"import ijson\n",
"import codecs"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"filename = \"rows.json\"\n",
"with open(filename, 'r') as f:\n",
" objects = ijson.items(f, 'meta.view.columns.item')\n",
" columns = list(objects)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{u'name': u'sid', u'format': {}, u'dataTypeName': u'meta_data', u'fieldName': u':sid', u'renderTypeName': u'meta_data', u'position': 0, u'id': -1, u'flags': [u'hidden']}\n"
]
}
],
"source": [
"print(columns[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[u':sid',\n",
" u':id',\n",
" u':position',\n",
" u':created_at',\n",
" u':created_meta',\n",
" u':updated_at',\n",
" u':updated_meta',\n",
" u':meta',\n",
" u'date_of_stop',\n",
" u'time_of_stop',\n",
" u'agency',\n",
" u'subagency',\n",
" u'description',\n",
" u'location',\n",
" u'latitude',\n",
" u'longitude',\n",
" u'accident',\n",
" u'belts',\n",
" u'personal_injury',\n",
" u'property_damage',\n",
" u'fatal',\n",
" u'commercial_license',\n",
" u'hazmat',\n",
" u'commercial_vehicle',\n",
" u'alcohol',\n",
" u'work_zone',\n",
" u'state',\n",
" u'vehicle_type',\n",
" u'year',\n",
" u'make',\n",
" u'model',\n",
" u'color',\n",
" u'violation_type',\n",
" u'charge',\n",
" u'article',\n",
" u'contributed_to_accident',\n",
" u'race',\n",
" u'gender',\n",
" u'driver_city',\n",
" u'driver_state',\n",
" u'dl_state',\n",
" u'arrest_type',\n",
" u'geolocation']"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"column_names = [col[\"fieldName\"] for col in columns]\n",
"column_names"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"good_columns = [\n",
" \"date_of_stop\", \n",
" \"time_of_stop\", \n",
" \"agency\", \n",
" \"subagency\",\n",
" \"description\",\n",
" \"location\", \n",
" \"latitude\", \n",
" \"longitude\", \n",
" \"vehicle_type\", \n",
" \"year\", \n",
" \"make\", \n",
" \"model\", \n",
" \"color\", \n",
" \"violation_type\",\n",
" \"race\", \n",
" \"gender\", \n",
" \"driver_state\", \n",
" \"driver_city\", \n",
" \"dl_state\",\n",
" \"arrest_type\"\n",
"]\n",
"data = []\n",
"with open(filename, 'r') as f:\n",
" objects = ijson.items(f, 'data.item')\n",
" for row in objects:\n",
" selected_row = []\n",
" for item in good_columns:\n",
" selected_row.append(row[column_names.index(item)])\n",
" data.append(selected_row)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df[\"date_of_stop\"]=pd.to_datetime(df[\"date_of_stop\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.DataFrame(data, columns=good_columns)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df.to_csv(\"rows.csv\",sep=\",\", encoding='UTF-8')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ds = pd.read_csv(\"rows.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from pymongo import MongoClient\n",
"from datetime import datetime\n",
"client = MongoClient()\n",
"client = MongoClient('localhost', 27017)\n",
"db = client['Assignment']\n",
"posts = db.collections\n",
"posts.insert_many(df.to_dict('record'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
" client.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"client = MongoClient('localhost', 27017)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"db = client['Assignment']\n",
"collections = db.collections"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Q5. how many stops are made by car color\n",
"car_stops = collections.aggregate([{\"$group\" : {\"_id\":\"$color\", \"count\":{\"$sum\":1}}}])\n",
"for No in car_stops:\n",
" print No"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Q6 Find the value counts of arrest type\n",
"arrest_type =collections.aggregate([{\"$group\" : {\"_id\":\"$arrest_type\", \"count\":{\"$sum\":1}}}])\n",
"for No in arrest_type:\n",
" print No"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df[\"date_of_stop\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Q7 Find which days result in the most traffic stop\n",
"Days=collections.aggregate([{\"$project\":{\"No_of_daysRes\": { \"$dayOfWeek\": \"$date_of_stop\" },} },{\n",
" \"$group\": {\"_id\":\"$No_of_daysRes\", \"count\":{\"$sum\":1}}}])\n",
"\n",
"for doc in Days:\n",
" print doc"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.11+"
}
},
"nbformat": 4,
"nbformat_minor": 2
}