Created
November 21, 2014 21:17
-
-
Save yudetamago/f3473696565642b6b2bf to your computer and use it in GitHub Desktop.
This file contains hidden or 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 | |
import numpy as np | |
class DataFormatter: | |
""" | |
データを読み込んで整形して返すクラスです。 | |
""" | |
__NALimit = 3 | |
@classmethod | |
def fromCSV(cls, fileName): | |
""" | |
CSVからデータを読み込んで整形する。 | |
""" | |
df = pd.read_csv(fileName) | |
df = cls.__exclude(df, cls.__NALimit) | |
df = cls.__interpolate(df) | |
return df | |
@classmethod | |
def __exclude(cls, df, limit): | |
""" | |
欠損値がlimit数以上のレコードを除外する。 | |
""" | |
nanToInt = lambda x:(1 if np.isnan(x) else 0) | |
return df[df.applymap(nanToInt).sum(axis=1).apply(lambda x:x<=limit)] | |
@classmethod | |
def __interpolate(cls, df): | |
""" | |
欠損値を平均値で補完する。 | |
""" | |
return df.fillna(np.round(df.mean())) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment