數(shù)據(jù)松弛作用：

train和test的特征各自去掉頻率不一致的取值，讓train和test關(guān)于某特征的各種取值的概率分布全都一致。

?

松弛代碼：

?

import pandas as pd import numpy as np import multiprocessing import warnings import matplotlib.pyplot as plt import seaborn as sns import lightgbm as lgb import gc from time import time import datetime import matplotlib.pyplot as plt from tqdm import tqdm_notebook from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import StratifiedKFold, KFold, TimeSeriesSplit, train_test_split from sklearn.metrics import roc_auc_score from sklearn.tree import DecisionTreeClassifier from sklearn import tree import graphviz import pandas as pd import datatable as dt warnings.simplefilter('ignore') sns.set()def reduce_mem_usage(df, verbose=True):numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']start_mem = df.memory_usage(deep=True).sum() / 1024**2for col in df.columns:col_type = df[col].dtypesif col_type in numerics: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:c_prec = df[col].apply(lambda x: np.finfo(x).precision).max()if c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max and c_prec == np.finfo(np.float32).precision:df[col] = df[col].astype(np.float32)else:df[col] = df[col].astype(np.float64)end_mem = df.memory_usage().sum() / 1024**2if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))return df def plot_numerical(feature):fig, axes = plt.subplots(nrows=3, ncols=2, figsize=(16, 18))sns.kdeplot(train[feature], ax=axes[0][0], label='Train');#第1行圖的第1幅圖sns.kdeplot(test[feature], ax=axes[0][0], label='Test');#第1行圖的第1幅圖sns.kdeplot(train[train['isFraud']==0][feature], ax=axes[0][1], label='isFraud 0')sns.kdeplot(train[train['isFraud']==1][feature], ax=axes[0][1], label='isFraud 1')test[feature].index += len(train)axes[1][0].plot(train[feature], '.', label='Train');#第2行圖的第1幅圖axes[1][0].plot(test[feature], '.', label='Test');axes[1][0].set_xlabel('Row index');axes[1][0].legend()test[feature].index -= len(train)#減去偏置時間axes[1][1].plot(train[train['isFraud']==0][feature], '.', label='isFraud 0');axes[1][1].plot(train[train['isFraud']==1][feature], '.', label='isFraud 1');axes[1][1].set_xlabel('row index');axes[1][1].legend()pd.DataFrame({'train': [train[feature].isnull().sum()], 'test': [test[feature].isnull().sum()]}).plot(kind='bar', rot=0, ax=axes[2][0]);pd.DataFrame({'isFraud 0': [train[(train['isFraud']==0) & (train[feature].isnull())][feature].shape[0]],'isFraud 1': [train[(train['isFraud']==1) & (train[feature].isnull())][feature].shape[0]]}).plot(kind='bar', rot=0, ax=axes[2][1]);fig.suptitle(feature, fontsize=18);#第1行的兩個子圖axes[0][0].set_title('Train/Test KDE distribution');axes[0][1].set_title('Target value KDE distribution');#第2行的兩個子圖axes[1][0].set_title('Index versus value: Train/Test distribution');axes[1][1].set_title('Index versus value: Target distribution');#第3行的兩個子圖axes[2][0].set_title('Number of NaNs');axes[2][1].set_title('Target value distribution among NaN values');plt.show()def relax_data(df_train, df_test, col):cv1 = pd.DataFrame(df_train[col].value_counts().reset_index().rename({col:'train'},axis=1))cv2 = pd.DataFrame(df_test[col].value_counts().reset_index().rename({col:'test'},axis=1))cv3 = pd.merge(cv1,cv2,on='index',how='outer')factor = len(df_test)/len(df_train)cv3['train'].fillna(0,inplace=True)cv3['test'].fillna(0,inplace=True)cv3['remove'] = Falsecv3['remove'] = cv3['remove'] | (cv3['train'] < len(df_train)/10000)cv3['remove'] = cv3['remove'] | (factor*cv3['train'] < cv3['test']/3)cv3['remove'] = cv3['remove'] | (factor*cv3['train'] > 3*cv3['test'])cv3['new'] = cv3.apply(lambda x: x['index'] if x['remove']==False else 0,axis=1)cv3['new'],_ = cv3['new'].factorize(sort=True)cv3.set_index('index',inplace=True)cc = cv3['new'].to_dict()df_train[col] = df_train[col].map(cc)df_test[col] = df_test[col].map(cc)return df_train, df_test

數(shù)據(jù)準備：

train=pd.read_csv('./ieee-fraud-detection/train1.csv') train=reduce_mem_usage(train) test =pd.read_csv('./ieee-fraud-detection/test1.csv') test=reduce_mem_usage(test)

?

松弛前的效果：

plot_numerical('C7')

?

松弛后的效果：

train, test = relax_data(train, test, 'C7') plot_numerical('C7')

總結(jié)

以上是生活随笔為你收集整理的数据松弛Data Relaxation的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。