1.数据抽取
2.特征工程
3.算法对比
4.xgboost
import numpy as npimport pandas as pdpd.set_option('display.max_rows', 500)pd.set_option('display.max_columns', 100)from itertools import productfrom sklearn.preprocessing import LabelEncoderimport seaborn as snsimport matplotlib.pyplot as plt%matplotlib inlinefrom xgboost import XGBRegressorfrom xgboost import plot_importancedef plot_features(booster, figsize): fig, ax = plt.subplots(1,1,figsize=figsize)return plot_importance(booster=booster, ax=ax)import timeimport sysimport gcimport picklesys.version_infoitems = pd.read_csv('D:/anaconda_coding/xgboost/items.csv')shops = pd.read_csv('D:/anaconda_coding/xgboost/shops.csv')cats = pd.read_csv('D:/anaconda_coding/xgboost/item_categories.csv')train = pd.read_csv('D:/anaconda_coding/xgboost/sales_train_v2.csv')# set index to ID to avoid droping it latertest = pd.read_csv('D:/anaconda_coding/xgboost/test.csv').set_index('ID')test.head()plt.figure(figsize=(10,4))plt.xlim(-100, 3000)sns.boxplot(x=train.item_cnt_day)plt.figure(figsize=(10,4))plt.xlim(train.item_price.min(), train.item_price.max()*1.1)sns.boxplot(x=train.item_price)train = train[train.item_price<100000]##筛选数据挑出价格小于100000，销售产品数量小于1000的训练数据train = train[train.item_cnt_day<1001]train.head()##用中值去填充价格小于0的那一栏数据median = train[(train.shop_id==32)&(train.item_id==2973)&(train.date_block_num==4)&(train.item_price>0)].item_price.median()train.loc[train.item_price<0, 'item_price'] = mediantrain['item_price'].value_counts().min()# 56train.loc[train.shop_id == 0, 'shop_id'] = 57test.loc[test.shop_id == 0, 'shop_id'] = 57#train.loc[train.shop_id == 1, 'shop_id'] = 58test.loc[test.shop_id == 1, 'shop_id'] = 58train.loc[train.shop_id == 10, 'shop_id'] = 11test.loc[test.shop_id == 10, 'shop_id'] = 11shops.loc[shops.shop_name == 'Сергиев Посад ТЦ "7Я"', 'shop_name'] = 'СергиевПосад ТЦ "7Я"'shops['city'] = shops['shop_name'].str.split(' ').map(lambda x: x[0])shops.loc[shops.city == '!Якутск', 'city'] = 'Якутск'shops['city_code'] = LabelEncoder().fit_transform(shops['city'])shops = shops[['shop_id','city_code']]cats['split'] = cats['item_category_name'].str.split('-')cats['type'] = cats['split'].map(lambda x: x[0].strip())cats['type_code'] = LabelEncoder().fit_transform(cats['type'])# if subtype is nan then typecats['subtype'] = cats['split'].map(lambda x: x[1].strip() if len(x) > 1 else x[0].strip())cats['subtype_code'] = LabelEncoder().fit_transform(cats['subtype'])cats = cats[['item_category_id','type_code', 'subtype_code']]items.drop(['item_name'], axis=1, inplace=True)shops.head()len(list(set(test.item_id) - set(test.item_id).intersection(set(train.item_id)))), len(list(set(test.item_id))), len(test)ts = time.time()matrix = []cols = ['date_block_num','shop_id','item_id']for i in range(34):sales = train[train.date_block_num==i]matrix.append(np.array(list(product([i], sales.shop_id.unique(), sales.item_id.unique())), dtype='int16'))matrix = pd.DataFrame(np.vstack(matrix), columns=cols)matrix['date_block_num'] = matrix['date_block_num'].astype(np.int8)matrix['shop_id'] = matrix['shop_id'].astype(np.int8)matrix['item_id'] = matrix['item_id'].astype(np.int16)matrix.sort_values(cols,inplace=True)time.time() - tstrain['revenue'] = train['item_price'] * train['item_cnt_day']ts = time.time()group = train.groupby(['date_block_num','shop_id','item_id']).agg({'item_cnt_day': ['sum']})group.columns = ['item_cnt_month']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=cols, how='left')matrix['item_cnt_month'] = (matrix['item_cnt_month'].fillna(0).clip(0,20) # NB clip target here.astype(np.float16))time.time() - tstest['date_block_num'] = 34test['date_block_num'] = test['date_block_num'].astype(np.int8)test['shop_id'] = test['shop_id'].astype(np.int8)test['item_id'] = test['item_id'].astype(np.int16)test.head()ts = time.time()matrix = pd.concat([matrix, test], ignore_index=True, sort=False, keys=cols)matrix.fillna(0, inplace=True) # 34 monthprint(matrix.head())time.time() - tsts = time.time()matrix = pd.merge(matrix, shops, on=['shop_id'], how='left')matrix = pd.merge(matrix, items, on=['item_id'], how='left')matrix = pd.merge(matrix, cats, on=['item_category_id'], how='left')matrix['city_code'] = matrix['city_code'].astype(np.int8)matrix['item_category_id'] = matrix['item_category_id'].astype(np.int8)matrix['type_code'] = matrix['type_code'].astype(np.int8)matrix['subtype_code'] = matrix['subtype_code'].astype(np.int8)time.time() - tsdef lag_feature(df, lags, col):tmp = df[['date_block_num','shop_id','item_id',col]]for i in lags:shifted = tmp.copy()shifted.columns = ['date_block_num','shop_id','item_id', col+'_lag_'+str(i)]shifted['date_block_num'] += idf = pd.merge(df, shifted, on=['date_block_num','shop_id','item_id'], how='left')return dfts = time.time()matrix = lag_feature(matrix, [1,2,3,6,12], 'item_cnt_month')time.time() - tsts = time.time()group = matrix.groupby(['date_block_num']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num'], how='left')matrix['date_avg_item_cnt'] = matrix['date_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_avg_item_cnt')matrix.drop(['date_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'item_id']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_item_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num','item_id'], how='left')matrix['date_item_avg_item_cnt'] = matrix['date_item_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1,2,3,6,12], 'date_item_avg_item_cnt')matrix.drop(['date_item_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'shop_id']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_shop_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num','shop_id'], how='left')matrix['date_shop_avg_item_cnt'] = matrix['date_shop_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1,2,3,6,12], 'date_shop_avg_item_cnt')matrix.drop(['date_shop_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'item_category_id']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_cat_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num','item_category_id'], how='left')matrix['date_cat_avg_item_cnt'] = matrix['date_cat_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_cat_avg_item_cnt')matrix.drop(['date_cat_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'shop_id', 'item_category_id']).agg({'item_cnt_month': ['mean']})group.columns = ['date_shop_cat_avg_item_cnt']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'shop_id', 'item_category_id'], how='left')matrix['date_shop_cat_avg_item_cnt'] = matrix['date_shop_cat_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_shop_cat_avg_item_cnt')matrix.drop(['date_shop_cat_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'shop_id', 'type_code']).agg({'item_cnt_month': ['mean']})group.columns = ['date_shop_type_avg_item_cnt']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'shop_id', 'type_code'], how='left')matrix['date_shop_type_avg_item_cnt'] = matrix['date_shop_type_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_shop_type_avg_item_cnt')matrix.drop(['date_shop_type_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'shop_id', 'subtype_code']).agg({'item_cnt_month': ['mean']})group.columns = ['date_shop_subtype_avg_item_cnt']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'shop_id', 'subtype_code'], how='left')matrix['date_shop_subtype_avg_item_cnt'] = matrix['date_shop_subtype_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_shop_subtype_avg_item_cnt')matrix.drop(['date_shop_subtype_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'city_code']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_city_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'city_code'], how='left')matrix['date_city_avg_item_cnt'] = matrix['date_city_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_city_avg_item_cnt')matrix.drop(['date_city_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'item_id', 'city_code']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_item_city_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'item_id', 'city_code'], how='left')matrix['date_item_city_avg_item_cnt'] = matrix['date_item_city_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_item_city_avg_item_cnt')matrix.drop(['date_item_city_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'type_code']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_type_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'type_code'], how='left')matrix['date_type_avg_item_cnt'] = matrix['date_type_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_type_avg_item_cnt')matrix.drop(['date_type_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = matrix.groupby(['date_block_num', 'subtype_code']).agg({'item_cnt_month': ['mean']})group.columns = [ 'date_subtype_avg_item_cnt' ]group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num', 'subtype_code'], how='left')matrix['date_subtype_avg_item_cnt'] = matrix['date_subtype_avg_item_cnt'].astype(np.float16)matrix = lag_feature(matrix, [1], 'date_subtype_avg_item_cnt')matrix.drop(['date_subtype_avg_item_cnt'], axis=1, inplace=True)time.time() - tsts = time.time()group = train.groupby(['item_id']).agg({'item_price': ['mean']})group.columns = ['item_avg_item_price']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['item_id'], how='left')matrix['item_avg_item_price'] = matrix['item_avg_item_price'].astype(np.float16)group = train.groupby(['date_block_num','item_id']).agg({'item_price': ['mean']})group.columns = ['date_item_avg_item_price']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num','item_id'], how='left')matrix['date_item_avg_item_price'] = matrix['date_item_avg_item_price'].astype(np.float16)lags = [1,2,3,4,5,6]matrix = lag_feature(matrix, lags, 'date_item_avg_item_price')for i in lags:matrix['delta_price_lag_'+str(i)] = \(matrix['date_item_avg_item_price_lag_'+str(i)] - matrix['item_avg_item_price']) / matrix['item_avg_item_price']def select_trend(row):for i in lags:if row['delta_price_lag_'+str(i)]:return row['delta_price_lag_'+str(i)]return 0matrix['delta_price_lag'] = matrix.apply(select_trend, axis=1)matrix['delta_price_lag'] = matrix['delta_price_lag'].astype(np.float16)matrix['delta_price_lag'].fillna(0, inplace=True)# matrix['price_trend'] = matrix[['delta_price_lag_1','delta_price_lag_2','delta_price_lag_3']].bfill(axis=1).iloc[:, 0]# Invalid dtype for backfill_2d [float16]fetures_to_drop = ['item_avg_item_price', 'date_item_avg_item_price']for i in lags:fetures_to_drop += ['date_item_avg_item_price_lag_'+str(i)]fetures_to_drop += ['delta_price_lag_'+str(i)]matrix.drop(fetures_to_drop, axis=1, inplace=True)time.time() - tsts = time.time()group = train.groupby(['date_block_num','shop_id']).agg({'revenue': ['sum']})group.columns = ['date_shop_revenue']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['date_block_num','shop_id'], how='left')matrix['date_shop_revenue'] = matrix['date_shop_revenue'].astype(np.float32)group = group.groupby(['shop_id']).agg({'date_shop_revenue': ['mean']})group.columns = ['shop_avg_revenue']group.reset_index(inplace=True)matrix = pd.merge(matrix, group, on=['shop_id'], how='left')matrix['shop_avg_revenue'] = matrix['shop_avg_revenue'].astype(np.float32)matrix['delta_revenue'] = (matrix['date_shop_revenue'] - matrix['shop_avg_revenue']) / matrix['shop_avg_revenue']matrix['delta_revenue'] = matrix['delta_revenue'].astype(np.float16)matrix = lag_feature(matrix, [1], 'delta_revenue')matrix.drop(['date_shop_revenue','shop_avg_revenue','delta_revenue'], axis=1, inplace=True)time.time() - tsmatrix['month'] = matrix['date_block_num'] % 12matrix.head()days = pd.Series([31,28,31,30,31,30,31,31,30,31,30,31])matrix['days'] = matrix['month'].map(days).astype(np.int8)ts = time.time()cache = {}matrix['item_shop_last_sale'] = -1matrix['item_shop_last_sale'] = matrix['item_shop_last_sale'].astype(np.int8)for idx, row in matrix.iterrows(): key = str(row.item_id)+' '+str(row.shop_id)if key not in cache:if row.item_cnt_month!=0:cache[key] = row.date_block_numelse:last_date_block_num = cache[key]matrix.at[idx, 'item_shop_last_sale'] = row.date_block_num - last_date_block_numcache[key] = row.date_block_num time.time() - tsts = time.time()cache = {}matrix['item_last_sale'] = -1matrix['item_last_sale'] = matrix['item_last_sale'].astype(np.int8)for idx, row in matrix.iterrows(): key = row.item_idif key not in cache:if row.item_cnt_month!=0:cache[key] = row.date_block_numelse:last_date_block_num = cache[key]if row.date_block_num>last_date_block_num:matrix.at[idx, 'item_last_sale'] = row.date_block_num - last_date_block_numcache[key] = row.date_block_num time.time() - tsts = time.time()matrix['item_shop_first_sale'] = matrix['date_block_num'] - matrix.groupby(['item_id','shop_id'])['date_block_num'].transform('min')matrix['item_first_sale'] = matrix['date_block_num'] - matrix.groupby('item_id')['date_block_num'].transform('min')time.time() - tsts = time.time()matrix = matrix[matrix.date_block_num > 11]time.time() - tsts = time.time()def fill_na(df):for col in df.columns:if ('_lag_' in col) & (df[col].isnull().any()):if ('item_cnt' in col):df[col].fillna(0, inplace=True) return dfmatrix = fill_na(matrix)time.time() - tsmatrix.to_pickle('data.pkl')del matrixdel cachedel groupdel itemsdel shopsdel catsdel train# leave test for submissiongc.collect();
5.数据大小优化、xgboost跑模型
data = pd.read_pickle('data.pkl')data = data[['date_block_num','shop_id','item_id','item_cnt_month','city_code','item_category_id','type_code','subtype_code','item_cnt_month_lag_1','item_cnt_month_lag_2','item_cnt_month_lag_3','item_cnt_month_lag_6','item_cnt_month_lag_12','date_avg_item_cnt_lag_1','date_item_avg_item_cnt_lag_1','date_item_avg_item_cnt_lag_2','date_item_avg_item_cnt_lag_3','date_item_avg_item_cnt_lag_6','date_item_avg_item_cnt_lag_12','date_shop_avg_item_cnt_lag_1','date_shop_avg_item_cnt_lag_2','date_shop_avg_item_cnt_lag_3','date_shop_avg_item_cnt_lag_6','date_shop_avg_item_cnt_lag_12','date_cat_avg_item_cnt_lag_1','date_shop_cat_avg_item_cnt_lag_1',#'date_shop_type_avg_item_cnt_lag_1',#'date_shop_subtype_avg_item_cnt_lag_1','date_city_avg_item_cnt_lag_1','date_item_city_avg_item_cnt_lag_1',#'date_type_avg_item_cnt_lag_1',#'date_subtype_avg_item_cnt_lag_1','delta_price_lag','month','days','item_shop_last_sale','item_last_sale','item_shop_first_sale','item_first_sale',]]X_train = data[data.date_block_num < 33].drop(['item_cnt_month'], axis=1)Y_train = data[data.date_block_num < 33]['item_cnt_month']X_valid = data[data.date_block_num == 33].drop(['item_cnt_month'], axis=1)Y_valid = data[data.date_block_num == 33]['item_cnt_month']X_test = data[data.date_block_num == 34].drop(['item_cnt_month'], axis=1)del datagc.collect();ts = time.time()model = XGBRegressor(max_depth=8,n_estimators=1000,min_child_weight=300, colsample_bytree=0.8, subsample=0.8, eta=0.3, seed=42)model.fit(X_train, Y_train, eval_metric="rmse", eval_set=[(X_train, Y_train), (X_valid, Y_valid)], verbose=True, early_stopping_rounds = 10)time.time() - ts
Y_pred = model.predict(X_valid).clip(0, 20)Y_test = model.predict(X_test).clip(0, 20)submission = pd.DataFrame({"ID": test.index, "item_cnt_month": Y_test})submission.to_csv('xgb_submission.csv', index=False)# save predictions for an ensemblepickle.dump(Y_pred, open('xgb_train.pickle', 'wb'))pickle.dump(Y_test, open('xgb_test.pickle', 'wb'))plot_features(model, (10,14))
