天猫用户复购预测之特征工程构建1
导入包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import gc
from collections import Counter
import copy
import warnings
warnings.filterwarnings("ignore")
#读取数据集
#test_data = pd.read_csv('./data_format1/test_format1.csv')
#train_data = pd.read_csv('./data_format1/train_format1.csv')
#user_info = pd.read_csv('./data_format1/user_info_format1.csv')
#user_log = pd.read_csv('./data_format1/user_log_format1.csv')数据内存压缩（对源码这部分有一定的修改，鉴于内存原因）
def read_csv(file_name, num_rows):
return pd.read_csv(file_name, nrows=num_rows, encoding='gbk')
# reduce memory # 内存压缩轮子
def reduce_mem_usage(df, verbose=True):
start_mem = df.memory_usage().sum() / 1024 ** 2
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
for col in df.columns:
col_type = df[col].dtypes
if 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)
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)
end_mem = df.memory_usage().sum() / 1024 ** 2
print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
return df
num_rows = None
#num_rows = 2000 # 1000条测试代码使用
train_file = '天猫数据/train_format1.csv'
test_file = '天猫数据/test_format1.csv'
user_info_file = '天猫数据/user_info_format1.csv'
user_log_file = '天猫数据/user_log_format1.csv'
# 进行压缩
train_data = reduce_mem_usage(read_csv(train_file, num_rows))
test_data = reduce_mem_usage(read_csv(test_file, num_rows))
user_info = reduce_mem_usage(read_csv(user_info_file, num_rows))
user_log = reduce_mem_usage(read_csv(user_log_file, num_rows))
构造特征
# 开始构造特征
# 合并用户信息
all_data = train_data.append(test_data) # 纵向按列拼接
print(all_data)
all_data = all_data.merge(user_info, on=['user_id'], how='left')
del train_data, test_data, user_info
gc.collect()
print(all_data)
"""
按时间排序
"""
user_log = user_log.sort_values(['user_id', 'time_stamp'])
"""
合并数据 之 item_id:商品ID cat_id:商品类目id seller_id:店铺ID brand_id:品牌ID time_tamp:行为发生时间 action_type:行为类型
"""
list_join_func = lambda x: " ".join([str(i) for i in x])
agg_dict = {
'item_id' : list_join_func,
'cat_id' : list_join_func,
'seller_id' : list_join_func,
'brand_id' : list_join_func,
'time_stamp' : list_join_func,
'action_type' : list_join_func
}
rename_dict = {
'item_id' : 'item_path',
'cat_id' : 'cat_path',
'seller_id' : 'seller_path',
'brand_id' : 'brand_path',
'time_stamp' : 'time_stamp_path',
'action_type' : 'action_type_path'
}
# 从用户角度合并数据 重构索引以及再合并all_data
def merge_list(df_ID, join_columns, df_data, agg_dict, rename_dict):
df_data = df_data.\
groupby(join_columns).\
agg(agg_dict).\
reset_index().\
rename(columns=rename_dict)
df_ID = df_ID.merge(df_data, on=join_columns, how="left")
return df_ID
all_data = merge_list(all_data, 'user_id', user_log, agg_dict, rename_dict)
"""
删除不需要的数据
"""
del user_log
gc.collect()
print(all_data.head(20))
print(all_data['item_path'].head(10))
# 定义统计量为构建特征做准备
def cnt_(x):
try:
return len(x.split(' '))
except:
return -1
def nunique_(x):
try:
return len(set(x.split(' ')))
except:
return -1
def max_(x):
try:
return np.max([int(i) for i in x.split(' ')])
except:
return -1
def min_(x):
try:
return np.min([int(i) for i in x.split(' ')])
except:
return -1
# 方差
def std_(x):
try:
return np.std([float(i) for i in x.split(' ')])
except:
return -1
# 统计数据中top N的数据
def most_n(x, n):
try:
return Counter(x.split(' ')).most_common(n)[n-1][0]
except:
return -1
# 统计数据中top N数据的总数
def most_n_cnt(x, n):
try:
return Counter(x.split(' ')).most_common(n)[n-1][1]
except:
return -1
###
def user_cnt(df_data, single_col, name):
df_data[name] = df_data[single_col].apply(cnt_)
return df_data
def user_nunique(df_data, single_col, name):
df_data[name] = df_data[single_col].apply(nunique_)
return df_data
def user_max(df_data, single_col, name):
df_data[name] = df_data[single_col].apply(max_)
return df_data
def user_min(df_data, single_col, name):
df_data[name] = df_data[single_col].apply(min_)
return df_data
def user_std(df_data, single_col, name):
df_data[name] = df_data[single_col].apply(std_)
return df_data
def user_most_n(df_data, single_col, name, n=1):
func = lambda x: most_n(x, n)
df_data[name] = df_data[single_col].apply(func)
return df_data
def user_most_n_cnt(df_data, single_col, name, n=1):
func = lambda x: most_n_cnt(x, n)
df_data[name] = df_data[single_col].apply(func)
return df_data
"""
提取基本统计特征
"""
all_data_test = all_data.head(2000)
#all_data_test = all_data
# 统计用户 点击、浏览、加购、购买行为
# 统计每个用户逛店的总次数
all_data_test = user_cnt(all_data_test, 'seller_path', 'user_cnt')
# 统计每个用户逛店不同店铺种数
all_data_test = user_nunique(all_data_test, 'seller_path', 'seller_nunique')
# 统计每个用户逛不同品类种数
all_data_test = user_nunique(all_data_test, 'cat_path', 'cat_nunique')
# 统计每个用户逛不同品牌种数
all_data_test = user_nunique(all_data_test, 'brand_path', 'brand_nunique')
# 统计每个用户逛不同商品种数
all_data_test = user_nunique(all_data_test, 'item_path', 'item_nunique')
# 统计每个用户总活跃天数 time_stamp_path格式为mmdd 即为月日格式（几月几号）
all_data_test = user_nunique(all_data_test, 'time_stamp_path', 'time_stamp_nunique')
# 统计每个用户不用行为种数
all_data_test = user_nunique(all_data_test, 'action_type_path', 'action_type_nunique')
# 最晚md时间
all_data_test = user_max(all_data_test, 'time_stamp_path', 'time_stamp_max')
# 最早md时间
all_data_test = user_min(all_data_test, 'time_stamp_path', 'time_stamp_min')
# 活跃天数方差：即波动情况
all_data_test = user_std(all_data_test, 'time_stamp_path', 'time_stamp_std')
# 最早和最晚相差天数
all_data_test['time_stamp_range'] = all_data_test['time_stamp_max'] - all_data_test['time_stamp_min']
# 用户最喜欢的店铺
all_data_test = user_most_n(all_data_test, 'seller_path', 'seller_most_1', n=1)
# 最喜欢的商品类目
all_data_test = user_most_n(all_data_test, 'cat_path', 'cat_most_1', n=1)
# 最喜欢的商品品牌
all_data_test = user_most_n(all_data_test, 'brand_path', 'brand_most_1', n=1)
# 最常见的行为动作
all_data_test = user_most_n(all_data_test, 'action_type_path', 'action_type_1', n=1)
# .....
# 用户最喜欢的店铺 行为（不区分种类）次数
all_data_test = user_most_n_cnt(all_data_test, 'seller_path', 'seller_most_1_cnt', n=1)
# 最喜欢的类目 行为（不区分种类）次数
all_data_test = user_most_n_cnt(all_data_test, 'cat_path', 'cat_most_1_cnt', n=1)
# 最喜欢的品牌 行为（不区分种类）次数
all_data_test = user_most_n_cnt(all_data_test, 'brand_path', 'brand_most_1_cnt', n=1)
# 最常见的行为动作 行为次数
all_data_test = user_most_n_cnt(all_data_test, 'action_type_path', 'action_type_1_cnt', n=1)
# .....
# 点击、加购、购买、收藏 分开统计
"""
统计基本特征函数
-- 知识点二
-- 根据不同行为的业务函数
-- 提取不同特征
"""
def col_cnt_(df_data, columns_list, action_type):
try:
data_dict = {}
col_list = copy.deepcopy(columns_list)
if action_type != None:
col_list += ['action_type_path']
for col in col_list:
data_dict[col] = df_data[col].split(' ')
path_len = len(data_dict[col])
data_out = []
for i_ in range(path_len):
data_txt = ''
for col_ in columns_list:
if data_dict['action_type_path'][i_] == action_type:
data_txt += '_' + data_dict[col_][i_]
data_out.append(data_txt)
return len(data_out)
except:
return -1
def col_nuique_(df_data, columns_list, action_type):
try:
data_dict = {}
col_list = copy.deepcopy(columns_list)
if action_type != None:
col_list += ['action_type_path']
for col in col_list:
data_dict[col] = df_data[col].split(' ')
path_len = len(data_dict[col])
data_out = []
for i_ in range(path_len):
data_txt = ''
for col_ in columns_list:
if data_dict['action_type_path'][i_] == action_type:
data_txt += '_' + data_dict[col_][i_]
data_out.append(data_txt)
return len(set(data_out))
except:
return -1
def user_col_cnt(df_data, columns_list, action_type, name):
df_data[name] = df_data.apply(lambda x: col_cnt_(x, columns_list, action_type), axis=1)
return df_data
def user_col_nunique(df_data, columns_list, action_type, name):
df_data[name] = df_data.apply(lambda x: col_nuique_(x, columns_list, action_type), axis=1)
return df_data
# 统计用户的点击店铺次数
all_data_test = user_col_cnt(all_data_test, ['seller_path'], '0', 'user_cnt_0')
# 统计用户的加购店铺次数
all_data_test = user_col_cnt(all_data_test, ['seller_path'], '1', 'user_cnt_1')
# 统计用户店铺购买次数
all_data_test = user_col_cnt(all_data_test, ['seller_path'], '2', 'user_cnt_2')
# 统计用户收藏店铺次数
all_data_test = user_col_cnt(all_data_test, ['seller_path'], '3', 'user_cnt_3')
# 统计用户点击不同店铺个数
all_data_test = user_col_nunique(all_data_test, ['seller_path'], '0', 'seller_nunique_0')
# ....
# 组合特征
# 点击次数
all_data_test = user_col_cnt(all_data_test, ['seller_path', 'item_path'], '0', 'user_cnt_0')
# 不同店铺个数
all_data_test = user_col_nunique(all_data_test, ['seller_path', 'item_path'], '0', 'seller_nunique_0')
# ....
print(all_data_test.columns)
特征构建2：词袋模型，词的嵌入以及模型融合的特征构建
# 利用countvector，tfidf提取特征 词袋模型
"""
-- 知识点四
-- 利用countvector，tfidf提取特征
"""
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, ENGLISH_STOP_WORDS
from scipy import sparse
# cntVec = CountVectorizer(stop_words=ENGLISH_STOP_WORDS, ngram_range=(1, 1), max_features=100)
tfidfVec = TfidfVectorizer(stop_words=ENGLISH_STOP_WORDS, ngram_range=(1, 1), max_features=100)
# columns_list = ['seller_path', 'cat_path', 'brand_path', 'action_type_path', 'item_path', 'time_stamp_path']
columns_list = ['seller_path']
for i, col in enumerate(columns_list):
tfidfVec.fit(all_data_test[col])
data_ = tfidfVec.transform(all_data_test[col])
if i == 0:
data_cat = data_
else:
data_cat = sparse.hstack((data_cat, data_))
# 特征重命名 特征合并
df_tfidf = pd.DataFrame(data_cat.toarray())
df_tfidf.columns = ['tfidf_' + str(i) for i in df_tfidf.columns]
all_data_test = pd.concat([all_data_test, df_tfidf], axis=1)
# 词的嵌入特征
import gensim
# Train Word2Vec model
model = gensim.models.Word2Vec(all_data_test['seller_path'].apply(lambda x: x.split(' ')), size=100, window=5, min_count=5, workers=4)
# model.save("product2vec.model")
# model = gensim.models.Word2Vec.load("product2vec.model")
def mean_w2v_(x, model, size=100):
try:
i = 0
for word in x.split(' '):
if word in model.wv.vocab:
i += 1
if i == 1:
vec = np.zeros(size)
vec += model.wv[word]
return vec / i
except:
return np.zeros(size)
def get_mean_w2v(df_data, columns, model, size):
data_array = []
for index, row in df_data.iterrows():
w2v = mean_w2v_(row[columns], model, size)
data_array.append(w2v)
return pd.DataFrame(data_array)
df_embeeding = get_mean_w2v(all_data_test, 'seller_path', model, 100)
df_embeeding.columns = ['embeeding_' + str(i) for i in df_embeeding.columns]
# 嵌入特征和原始特征合并
all_data_test = pd.concat([all_data_test, df_embeeding],axis=1)
# 多模型融合Stacking方法构建特征
"""
-- 知识点六
-- stacking特征
"""
from sklearn.model_selection import KFold
import pandas as pd
import numpy as np
from scipy import sparse
import xgboost
import lightgbm
from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier,GradientBoostingClassifier,ExtraTreesClassifier
from sklearn.ensemble import RandomForestRegressor,AdaBoostRegressor,GradientBoostingRegressor,ExtraTreesRegressor
from sklearn.linear_model import LinearRegression,LogisticRegression
from sklearn.svm import LinearSVC,SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import log_loss,mean_absolute_error,mean_squared_error
from sklearn.naive_bayes import MultinomialNB,GaussianNB
"""
-- 回归
-- stacking 回归特征
"""
def stacking_reg(clf,train_x,train_y,test_x,clf_name,kf,label_split=None):
train=np.zeros((train_x.shape[0],1))
test=np.zeros((test_x.shape[0],1))
test_pre=np.empty((folds,test_x.shape[0],1))
cv_scores=[]
for i,(train_index,test_index) in enumerate(kf.split(train_x,label_split)):
tr_x=train_x[train_index]
tr_y=train_y[train_index]
te_x=train_x[test_index]
te_y = train_y[test_index]
if clf_name in ["rf","ada","gb","et","lr"]:
clf.fit(tr_x,tr_y)
pre=clf.predict(te_x).reshape(-1,1)
train[test_index]=pre
test_pre[i,:]=clf.predict(test_x).reshape(-1,1)
cv_scores.append(mean_squared_error(te_y, pre))
elif clf_name in ["xgb"]:
train_matrix = clf.DMatrix(tr_x, label=tr_y, missing=-1)
test_matrix = clf.DMatrix(te_x, label=te_y, missing=-1)
z = clf.DMatrix(test_x, label=te_y, missing=-1)
params = {'booster': 'gbtree',
'eval_metric': 'rmse',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.03,
'tree_method': 'exact',
'seed': 2017,
'nthread': 12
}
num_round = 10000
early_stopping_rounds = 100
watchlist = [(train_matrix, 'train'),
(test_matrix, 'eval')
]
if test_matrix:
model = clf.train(params, train_matrix, num_boost_round=num_round,evals=watchlist,
early_stopping_rounds=early_stopping_rounds
)
pre= model.predict(test_matrix,ntree_limit=model.best_ntree_limit).reshape(-1,1)
train[test_index]=pre
test_pre[i, :]= model.predict(z, ntree_limit=model.best_ntree_limit).reshape(-1,1)
cv_scores.append(mean_squared_error(te_y, pre))
elif clf_name in ["lgb"]:
train_matrix = clf.Dataset(tr_x, label=tr_y)
test_matrix = clf.Dataset(te_x, label=te_y)
params = {
'boosting_type': 'gbdt',
'objective': 'regression_l2',
'metric': 'mse',
'min_child_weight': 1.5,
'num_leaves': 2**5,
'lambda_l2': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'learning_rate': 0.03,
'tree_method': 'exact',
'seed': 2017,
'nthread': 12,
'silent': True,
}
num_round = 10000
early_stopping_rounds = 100
if test_matrix:
model = clf.train(params, train_matrix,num_round,valid_sets=test_matrix,
early_stopping_rounds=early_stopping_rounds
)
pre= model.predict(te_x,num_iteration=model.best_iteration).reshape(-1,1)
train[test_index]=pre
test_pre[i, :]= model.predict(test_x, num_iteration=model.best_iteration).reshape(-1,1)
cv_scores.append(mean_squared_error(te_y, pre))
else:
raise IOError("Please add new clf.")
print("%s now score is:"%clf_name,cv_scores)
test[:]=test_pre.mean(axis=0)
print("%s_score_list:"%clf_name,cv_scores)
print("%s_score_mean:"%clf_name,np.mean(cv_scores))
return train.reshape(-1,1),test.reshape(-1,1)
def rf_reg(x_train, y_train, x_valid, kf, label_split=None):
randomforest = RandomForestRegressor(n_estimators=600, max_depth=20, n_jobs=-1, random_state=2017, max_features="auto",verbose=1)
rf_train, rf_test = stacking_reg(randomforest, x_train, y_train, x_valid, "rf", kf, label_split=label_split)
return rf_train, rf_test,"rf_reg"
def ada_reg(x_train, y_train, x_valid, kf, label_split=None):
adaboost = AdaBoostRegressor(n_estimators=30, random_state=2017, learning_rate=0.01)
ada_train, ada_test = stacking_reg(adaboost, x_train, y_train, x_valid, "ada", kf, label_split=label_split)
return ada_train, ada_test,"ada_reg"
def gb_reg(x_train, y_train, x_valid, kf, label_split=None):
gbdt = GradientBoostingRegressor(learning_rate=0.04, n_estimators=100, subsample=0.8, random_state=2017,max_depth=5,verbose=1)
gbdt_train, gbdt_test = stacking_reg(gbdt, x_train, y_train, x_valid, "gb", kf, label_split=label_split)
return gbdt_train, gbdt_test,"gb_reg"
def et_reg(x_train, y_train, x_valid, kf, label_split=None):
extratree = ExtraTreesRegressor(n_estimators=600, max_depth=35, max_features="auto", n_jobs=-1, random_state=2017,verbose=1)
et_train, et_test = stacking_reg(extratree, x_train, y_train, x_valid, "et", kf, label_split=label_split)
return et_train, et_test,"et_reg"
def lr_reg(x_train, y_train, x_valid, kf, label_split=None):
lr_reg=LinearRegression(n_jobs=-1)
lr_train, lr_test = stacking_reg(lr_reg, x_train, y_train, x_valid, "lr", kf, label_split=label_split)
return lr_train, lr_test, "lr_reg"
def xgb_reg(x_train, y_train, x_valid, kf, label_split=None):
xgb_train, xgb_test = stacking_reg(xgboost, x_train, y_train, x_valid, "xgb", kf, label_split=label_split)
return xgb_train, xgb_test,"xgb_reg"
def lgb_reg(x_train, y_train, x_valid, kf, label_split=None):
lgb_train, lgb_test = stacking_reg(lightgbm, x_train, y_train, x_valid, "lgb", kf, label_split=label_split)
return lgb_train, lgb_test,"lgb_reg"
"""
-- 分类
-- stacking 分类特征
"""
def stacking_clf(clf, train_x, train_y, test_x, clf_name, kf, label_split=None):
train = np.zeros((train_x.shape[0], 1))
test = np.zeros((test_x.shape[0], 1))
test_pre = np.empty((folds, test_x.shape[0], 1))
cv_scores = []
for i, (train_index, test_index) in enumerate(kf.split(train_x, label_split)):
tr_x = train_x[train_index]
tr_y = train_y[train_index]
te_x = train_x[test_index]
te_y = train_y[test_index]
if clf_name in ["rf", "ada", "gb", "et", "lr", "knn", "gnb"]:
clf.fit(tr_x, tr_y)
pre = clf.predict_proba(te_x)
train[test_index] = pre[:, 0].reshape(-1, 1)
test_pre[i, :] = clf.predict_proba(test_x)[:, 0].reshape(-1, 1)
cv_scores.append(log_loss(te_y, pre[:, 0].reshape(-1, 1)))
elif clf_name in ["xgb"]:
train_matrix = clf.DMatrix(tr_x, label=tr_y, missing=-1)
test_matrix = clf.DMatrix(te_x, label=te_y, missing=-1)
z = clf.DMatrix(test_x, label=te_y, missing=-1)
params = {'booster': 'gbtree',
'objective': 'multi:softprob',
'eval_metric': 'mlogloss',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.03,
'tree_method': 'exact',
'seed': 2017,
"num_class": 2
}
num_round = 10000
early_stopping_rounds = 100
watchlist = [(train_matrix, 'train'),
(test_matrix, 'eval')
]
if test_matrix:
model = clf.train(params, train_matrix, num_boost_round=num_round, evals=watchlist,
early_stopping_rounds=early_stopping_rounds
)
pre = model.predict(test_matrix, ntree_limit=model.best_ntree_limit)
train[test_index] = pre[:, 0].reshape(-1, 1)
test_pre[i, :] = model.predict(z, ntree_limit=model.best_ntree_limit)[:, 0].reshape(-1, 1)
cv_scores.append(log_loss(te_y, pre[:, 0].reshape(-1, 1)))
elif clf_name in ["lgb"]:
train_matrix = clf.Dataset(tr_x, label=tr_y)
test_matrix = clf.Dataset(te_x, label=te_y)
params = {
'boosting_type': 'gbdt',
# 'boosting_type': 'dart',
'objective': 'multiclass',
'metric': 'multi_logloss',
'min_child_weight': 1.5,
'num_leaves': 2 ** 5,
'lambda_l2': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'learning_rate': 0.03,
'tree_method': 'exact',
'seed': 2017,
"num_class": 2,
'silent': True,
}
num_round = 10000
early_stopping_rounds = 100
if test_matrix:
model = clf.train(params, train_matrix, num_round, valid_sets=test_matrix,
early_stopping_rounds=early_stopping_rounds
)
pre = model.predict(te_x, num_iteration=model.best_iteration)
train[test_index] = pre[:, 0].reshape(-1, 1)
test_pre[i, :] = model.predict(test_x, num_iteration=model.best_iteration)[:, 0].reshape(-1, 1)
cv_scores.append(log_loss(te_y, pre[:, 0].reshape(-1, 1)))
else:
raise IOError("Please add new clf.")
print("%s now score is:" % clf_name, cv_scores)
test[:] = test_pre.mean(axis=0)
print("%s_score_list:" % clf_name, cv_scores)
print("%s_score_mean:" % clf_name, np.mean(cv_scores))
return train.reshape(-1, 1), test.reshape(-1, 1)
def rf_clf(x_train, y_train, x_valid, kf, label_split=None):
randomforest = RandomForestClassifier(n_estimators=1200, max_depth=20, n_jobs=-1, random_state=2017,
max_features="auto", verbose=1)
rf_train, rf_test = stacking_clf(randomforest, x_train, y_train, x_valid, "rf", kf, label_split=label_split)
return rf_train, rf_test, "rf"
def ada_clf(x_train, y_train, x_valid, kf, label_split=None):
adaboost = AdaBoostClassifier(n_estimators=50, random_state=2017, learning_rate=0.01)
ada_train, ada_test = stacking_clf(adaboost, x_train, y_train, x_valid, "ada", kf, label_split=label_split)
return ada_train, ada_test, "ada"
def gb_clf(x_train, y_train, x_valid, kf, label_split=None):
gbdt = GradientBoostingClassifier(learning_rate=0.04, n_estimators=100, subsample=0.8, random_state=2017,
max_depth=5, verbose=1)
gbdt_train, gbdt_test = stacking_clf(gbdt, x_train, y_train, x_valid, "gb", kf, label_split=label_split)
return gbdt_train, gbdt_test, "gb"
def et_clf(x_train, y_train, x_valid, kf, label_split=None):
extratree = ExtraTreesClassifier(n_estimators=1200, max_depth=35, max_features="auto", n_jobs=-1, random_state=2017,
verbose=1)
et_train, et_test = stacking_clf(extratree, x_train, y_train, x_valid, "et", kf, label_split=label_split)
return et_train, et_test, "et"
def xgb_clf(x_train, y_train, x_valid, kf, label_split=None):
xgb_train, xgb_test = stacking_clf(xgboost, x_train, y_train, x_valid, "xgb", kf, label_split=label_split)
return xgb_train, xgb_test, "xgb"
def lgb_clf(x_train, y_train, x_valid, kf, label_split=None):
xgb_train, xgb_test = stacking_clf(lightgbm, x_train, y_train, x_valid, "lgb", kf, label_split=label_split)
return xgb_train, xgb_test, "lgb"
def gnb_clf(x_train, y_train, x_valid, kf, label_split=None):
gnb = GaussianNB()
gnb_train, gnb_test = stacking_clf(gnb, x_train, y_train, x_valid, "gnb", kf, label_split=label_split)
return gnb_train, gnb_test, "gnb"
def lr_clf(x_train, y_train, x_valid, kf, label_split=None):
logisticregression = LogisticRegression(n_jobs=-1, random_state=2017, C=0.1, max_iter=200)
lr_train, lr_test = stacking_clf(logisticregression, x_train, y_train, x_valid, "lr", kf, label_split=label_split)
return lr_train, lr_test, "lr"
def knn_clf(x_train, y_train, x_valid, kf, label_split=None):
kneighbors = KNeighborsClassifier(n_neighbors=200, n_jobs=-1)
knn_train, knn_test = stacking_clf(kneighbors, x_train, y_train, x_valid, "lr", kf, label_split=label_split)
return knn_train, knn_test, "knn"
# 获取训练和验证数据(为stacking特征做准备)
features_columns = [c for c in all_data_test.columns if c not in ['label', 'prob', 'seller_path', 'cat_path', 'brand_path', 'action_type_path', 'item_path', 'time_stamp_path']]
x_train = all_data_test[~all_data_test['label'].isna()][features_columns].values
y_train = all_data_test[~all_data_test['label'].isna()]['label'].values
x_valid = all_data_test[all_data_test['label'].isna()][features_columns].values
# 处理函数值inf以及nan情况
def get_matrix(data):
where_are_nan = np.isnan(data)
where_are_inf = np.isinf(data)
data[where_are_nan] = 0
data[where_are_inf] = 0
return data
x_train = np.float_(get_matrix(np.float_(x_train)))
y_train = np.int_(y_train)
x_valid = x_train
# 导入划分数据函数 设stacking特征为5折
from sklearn.model_selection import StratifiedKFold, KFold
folds = 5
seed = 1
kf = KFold(n_splits=5, shuffle=True, random_state=0)
# 使用lgb和xgb分类模型构造stacking特征
# clf_list = [lgb_clf, xgb_clf, lgb_reg, xgb_reg]
# clf_list_col = ['lgb_clf', 'xgb_clf', 'lgb_reg', 'xgb_reg']
clf_list = [lgb_clf, xgb_clf]
clf_list_col = ['lgb_clf', 'xgb_clf']
# 训练模型，获取stacking特征
clf_list = clf_list
column_list = []
train_data_list=[]
test_data_list=[]
for clf in clf_list:
train_data,test_data,clf_name=clf(x_train, y_train, x_valid, kf, label_split=None)
train_data_list.append(train_data)
test_data_list.append(test_data)
train_stacking = np.concatenate(train_data_list, axis=1)
test_stacking = np.concatenate(test_data_list, axis=1)
# 原始特征和stacking特征合并
# # 合并所有特征
train = pd.DataFrame(np.concatenate([x_train, train_stacking], axis=1))
test = np.concatenate([x_valid, test_stacking], axis=1)
# 特征重命名
df_train_all = pd.DataFrame(train)
df_train_all.columns = features_columns + clf_list_col
df_test_all = pd.DataFrame(test)
df_test_all.columns = features_columns + clf_list_col
# 获取数据ID以及特征标签LABEL
df_train_all['user_id'] = all_data_test[~all_data_test['label'].isna()]['user_id']
df_test_all['user_id'] = all_data_test[all_data_test['label'].isna()]['user_id']
df_train_all['label'] = all_data_test[~all_data_test['label'].isna()]['label']
# 训练数据和测试数据保存
df_train_all.to_csv('train_all.csv',header=True,index=False)
df_test_all.to_csv('test_all.csv',header=True,index=False)