Kaggle竞赛销售预测(xgboost)

1.数据抽取

2.特征工程

3.算法对比

4.xgboost

import numpy as np
import pandas as pd
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 100)

from itertools import product
from sklearn.preprocessing import LabelEncoder

import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

from xgboost import XGBRegressor
from xgboost import plot_importance

def plot_features(booster, figsize):    
    fig, ax = plt.subplots(1,1,figsize=figsize)
    return plot_importance(booster=booster, ax=ax)

import time
import sys
import gc
import pickle
sys.version_info

items = 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 later
test  = 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'] = median
train['item_price'].value_counts().min()

#  56
train.loc[train.shop_id == 0, 'shop_id'] = 57
test.loc[test.shop_id == 0, 'shop_id'] = 57
#
train.loc[train.shop_id == 1, 'shop_id'] = 58
test.loc[test.shop_id == 1, 'shop_id'] = 58

train.loc[train.shop_id == 10, 'shop_id'] = 11
test.loc[test.shop_id == 10, 'shop_id'] = 11

shops.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 type
cats['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() - ts

train['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'] = (ma