Created
July 13, 2017 09:13
-
-
Save ajoydas/f398a43b8fd70ca49f4ff841fbc0aa86 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
from pandas.io.json import json_normalize | |
from pymongo import MongoClient | |
import matplotlib.pyplot as plt | |
import re | |
import time | |
pd.set_option('display.expand_frame_repr', False) | |
def _connect_mongo(host, port, db): | |
conn = MongoClient(host, port) | |
return conn[db] | |
def read_mongo(db, collection, host, port): | |
""" Read from Mongo and Store into DataFrame """ | |
# Connect to MongoDB | |
db = _connect_mongo(host=host, port=port, db=db) | |
t0 = time.time() | |
cursor = db[collection].find({'created_at':{'$regex': '2013'}}, | |
no_cursor_timeout=True) | |
t1 = time.time() | |
total = t1-t0 | |
print total | |
cursor = list(cursor) | |
t2 = time.time() | |
total = t2-t0 | |
print total | |
df = json_normalize(cursor) | |
return df | |
# db = 'twittersmall' | |
# collection='twitterdata' | |
db = 'twitter' | |
collection='twitterCol' | |
#query={'lang':'{$exists: true}'} | |
host='localhost' | |
port=27017 | |
var = read_mongo(db, collection, host, port) | |
print var.head() | |
# yoo = pd.DataFrame() | |
# yoo['status'] = var['user.statuses_count'].head() | |
# print yoo | |
# yoo.sort_values(by='status', inplace=True, ascending=False) | |
# print yoo | |
var.sort_values(by='user.statuses_count', inplace=True, ascending=False) | |
print var.head() | |
# user=[] | |
# user.append(var.loc['_id'],['user.screen_name']]) | |
# print user | |
print var.columns | |
var = var.iloc[0:5] | |
df2 = var[['user.screen_name', 'user.statuses_count']] | |
print df2.columns | |
print df2.head() | |
#df2=df1.iloc[0:5] | |
print df2 | |
df2=df2.values | |
print df2 | |
names = [] | |
vals=[] | |
for x in range (0,5): | |
names.append(df2[x][0]) | |
vals.append(df2[x][1]) | |
print names | |
print vals | |
x_pos = list(range(len(names))) | |
width = 0.8 | |
fig, ax = plt.subplots() | |
plt.bar(x_pos, vals, width, alpha=1, color='g') | |
# Setting axis labels and ticks | |
ax.set_ylabel('Number of tweets', fontsize=15) | |
ax.set_title('Names', fontsize=10, fontweight='bold') | |
ax.set_xticks([p + 0.1 * width for p in x_pos]) | |
ax.set_xticklabels(names) | |
plt.setp(ax.get_xticklabels(), fontsize=10, rotation='vertical') | |
plt.grid() | |
plt.savefig('tweets_by_prg_language_1', format='png') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment