tweet_analytics

gistfile1.txt

#coding: utf-8
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
from datetime import datetime


df= pd.read_csv("/home/pi/tweets.csv")		#ここにCSVファイルのパスを入れる
df_tweet1 = df[df["text"] .str.contains(u"死にたい") == True]		#ここに抽出したいキーワードを入れる（以下2つも同様）
df_tweet2 = df[df["text"] .str.contains(u"お金") == True]
#df_tweet3 = df[df["text"] .str.contains(u"") == True]

ts = [datetime.strptime(x, "%Y-%m-%d %H:%M:%S +0000") for x in df_tweet1["timestamp"]]
ts = pd.to_datetime(ts)
ts = ts.to_period("M")

ts2 = [datetime.strptime(x, "%Y-%m-%d %H:%M:%S +0000") for x in df_tweet2["timestamp"]]
ts2 = pd.to_datetime(ts2)
ts2 = ts2.to_period("M")
"""
ts3 = [datetime.strptime(x, "%Y-%m-%d %H:%M:%S +0000") for x in df_tweet3["timestamp"]]
ts3 = pd.to_datetime(ts3)
ts3 = ts3.to_period("M")
"""
ts_counts = ts.value_counts()
ts_counts = ts_counts.sort_index()

ts_counts2 = ts2.value_counts()
ts_counts2 = ts_counts2.sort_index()
"""
ts_counts3 = ts3.value_counts()
ts_counts3 = ts_counts3.sort_index()
"""
ts_counts.plot(label = "wd")		#ここにデータの名前を入れる。日本語入力できません。
ts_counts2.plot(label = "No Money")
#ts_counts3.plot(label = "")

plt.legend()
plt.show()