Last active
April 11, 2017 17:02
-
-
Save hitowaft/1ce4daa0e5aaf4ecdbc902656c8436fb 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
# coding: utf-8 | |
# In[1]: | |
import pandas as pd | |
import numpy as np | |
import matplotlib.pyplot as plt | |
# In[2]: | |
tweet_df = pd.read_csv("/hoge/tweets.csv", parse_dates=["timestamp"]) #ここにcsvファイルのパスを入れる | |
tweet_df = tweet_df.set_index(["timestamp"]) | |
tweet_df = tweet_df.reindex(columns=["text"]) | |
# In[3]: | |
keyword = {"Yohei":"洋平|ようぺ"} #ここにキーワードを入れる | |
for k, v in keyword.items(): | |
tweet_df["{}".format(k)] = tweet_df["text"].str.contains("{}".format(v)) | |
new_df = tweet_df.drop(["text"], axis=1) | |
new_df = new_df.resample("M").sum() | |
# In[4]: | |
graph = [] | |
for i in range(1,13): | |
graph.append(new_df.loc[(new_df.index.month == i)].mean()) | |
graph = pd.DataFrame(graph, index=np.arange(1,13)) | |
graph.plot(kind="bar", legend=True) | |
plt.show() | |
#追記:以下は必要に応じて使ってください | |
""" | |
for i in keyword.values(): | |
print(tweet_df["text"][tweet_df["text"].str.contains("{}". format(i))]) | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment