Python对商店数据进行lstm和xgboost销售量时间序列建模预测分析

# 让我们导入EDA所需的库：


import numpy as np # 线性代数
import pandas as pd # 数据处理，CSV文件I / O导入（例如pd.read_csv）
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
plt.style.use("ggplot") # 绘图




#导入训练和测试文件：
train_df = pd.read_csv("../Data/train.csv")
test_df = pd.read_csv("../Data/test.csv")




#文件中有多少数据：
print("在训练集中，我们有", train_df.shape[0], "个观察值和", train_df.shape[1], 列/变量。")
print("在测试集中，我们有", test_df.shape[0], "个观察值和", test_df.shape[1], "列/变量。")
print("在商店集中，我们有", store_df.shape[0], "个观察值和", store_df.shape[1], "列/变量。")

#查看数据
train_df.head().append(train_df.tail()) #显示前5行。

train_df.isnull().all()
Out[5]:


Store            False
DayOfWeek        False
Date             False
Sales            False
Customers        False
Open             False
Promo            False
StateHoliday     False
SchoolHoliday    False
dtype: bool

opened_sales = (train_df[(train_df.Open == 1) #如果商店开业
opened_sales.Sales.describe()
Out[6]:


count    422307.000000
mean       6951.782199
std        3101.768685
min         133.000000
25%        4853.000000
50%        6367.000000
75%        8355.000000
max       41551.000000
Name: Sales, dtype: float64




<matplotlib.axes._subplots.AxesSubplot at 0x7f7c38fa6588>

In [9]:


train_df.Customers.describe()
Out[9]:


count    1.017209e+06
mean     6.331459e+02
std      4.644117e+02
min      0.000000e+00
25%      4.050000e+02
50%      6.090000e+02
75%      8.370000e+02
max      7.388000e+03
Name: Customers, dtype: float64


<matplotlib.axes._subplots.AxesSubplot at 0x7f7c3565d240>

train_df[(train_df.Customers > 6000)]

train_df.StateHoliday.value_counts()
 
0    855087
0    131072
a     20260
b      6690
c      4100
Name: StateHoliday, dtype: int64
 train_df.StateHoliday_cat.count()
 1017209
 train_df.tail()

train_df.isnull().all() #检查缺失
Out[18]:


Store               False
DayOfWeek           False
Date                False
Sales               False
Customers           False
Open                False
Promo               False
SchoolHoliday       False
StateHoliday_cat    False
dtype: bool

让我们继续进行商店分析

store_df.head().append(store_df.tail())

#缺失数据：




Store                         0.000000
StoreType                     0.000000
Assortment                    0.000000
CompetitionDistance           0.269058
CompetitionOpenSinceMonth    31.748879
CompetitionOpenSinceYear     31.748879
Promo2                        0.000000
Promo2SinceWeek              48.789238
Promo2SinceYear              48.789238
PromoInterval                48.789238
dtype: float64
In [21]:

store_df.CompetitionDistance.plot.box()

缺少数据，因为商店没有竞争。因此，我建议用零填充缺失的值。

store_df["CompetitionOpenSinceMonth"].fillna(0, inplace = True)

让我们看一下促销活动。

store_df.groupby(by = "Promo2", axis = 0).count()

f, ax = plt.subplots(2, 3, figsize = (20,10))


plt.subplots_adjust(hspace = 0.3)
plt.show()

sns.factorplot(data = train_store_df,
# 我们可以看到季节性，但看不到趋势。该销售额每年保持不变




<seaborn.axisgrid.FacetGrid at 0x7f7c350e0c50>

"CompetitionOpenSinceMonth", "CompetitionOpenSinceYear", "Promo2


<matplotlib.axes._subplots.AxesSubplot at 0x7f7c33d79c18>