Last active
August 29, 2015 14:26
-
-
Save m-note/6120d2ebb9b246e8e3c0 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
# recordDietの結果をPandasにまとめる | |
import pandas as pd | |
import os.path | |
def cleanText(text): | |
cleaned = text.replace('\n', ' ') # 改行記号を除く | |
cleaned = cleaned.strip() # 半角スペースを除く | |
cleaned = cleaned.replace(" ", "") # 全角スペースを除く | |
return cleaned | |
def intoDataFrame(extracted): | |
#各発言ごとに、リスト形式のものをdictに直してからpandasに渡す | |
count = 1 | |
for i in extracted: | |
if count == 1: | |
ext_df = pd.DataFrame([{cleanText(k): cleanText(v) for [k, v] in i}]) # If each dict represents a row, you could pass a list of dicts (http://goo.gl/t0uCHp) | |
else: | |
ext_df = ext_df.append(pd.DataFrame([{cleanText(k): cleanText(v) for [k, v] in i}])) # dataframeの結合絡み (http://goo.gl/8H6ER8) | |
count += 1 | |
# indexの設定 | |
ext_df.index = range(0, len(ext_df)) # cf. http://inaz2.hatenablog.com/entry/2013/04/09/002318 | |
return ext_df | |
# ext_df = intoDataFrame(recordDiet(speaker="安倍晋三", any="アベノミクス", Dfrom="2015-03-01", Duntil="2015-05-20")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment