Last active
March 22, 2020 05:22
-
-
Save zerebom/fc6e05163837988d9259c29a183a327e to your computer and use it in GitHub Desktop.
reduce_mem_usage description
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
def encode_categorical(df, cols): | |
for col in cols: | |
# Leave NaN as it is. | |
le = LabelEncoder() | |
not_null = df[col][df[col].notnull()] | |
df[col] = pd.Series(le.fit_transform(not_null), index=not_null.index) | |
return df |
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 | |
import numpy as np | |
def reduce_mem_usage(df, verbose=True): | |
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64'] | |
start_mem = df.memory_usage().sum() / 1024**2 | |
for col in df.columns: #columns毎に処理 | |
col_type = df[col].dtypes | |
if col_type in numerics: #numericsのデータ型の範囲内のときに処理を実行. データの最大最小値を元にデータ型を効率的なものに変更 | |
c_min = df[col].min() | |
c_max = df[col].max() | |
if str(col_type)[:3] == 'int': | |
if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max: | |
df[col] = df[col].astype(np.int8) | |
elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max: | |
df[col] = df[col].astype(np.int16) | |
elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max: | |
df[col] = df[col].astype(np.int32) | |
elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max: | |
df[col] = df[col].astype(np.int64) | |
else: | |
if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max: | |
df[col] = df[col].astype(np.float16) | |
elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max: | |
df[col] = df[col].astype(np.float32) | |
else: | |
df[col] = df[col].astype(np.float64) | |
end_mem = df.memory_usage().sum() / 1024**2 | |
if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem)) | |
return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
hoge