from datetime import datetime
import pandas as pd
import numpy as np
import matplotlib
from lib.evaluation import mape
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from definitions import ROOT_DIR
from global_sources.file_operation import read_feature_full, union_file
df_feature_full = read_feature_full()
df_predict = union_file('%s/%s' % (ROOT_DIR, 'sources/output/predict/'))
df_predict['rundate'] = df_predict['rundate'].astype('datetime64[ns]')
df_predict.columns = [
'rundate', 'storeid', 'goodscode', 'sales', 'pred_sale', 'pred_stock'
]
df_predict = pd.merge(df_predict,
df_feature_full,
how='left',
on=['goodscode', 'rundate'])
df_predict = df_predict[[
'goodscode', 'rundate', 'result', 'pred_sale', 'pred_stock'
]]
# print(len(df_result['rundate']))
# print(np.count_nonzero(df_result.isnull()))
# df_result['mape'] = (df_result['result'] - df_result['pred'])/df_result['result']
# df_result = df_result[['goodscode', 'mape']].abs()
df_feature_full['max_15'] = pd.qcut(df_feature_full['max_15'],
min(10, len(df_feature_full['max_15'].unique())), duplicates='drop').cat.codes
df_feature_full['sum_15'] = pd.qcut(df_feature_full['sum_15'],
min(10, len(df_feature_full['sum_15'].unique())), duplicates='drop').cat.codes
df_feature_full['min_7'] = pd.qcut(df_feature_full['min_7'],
min(10, len(df_feature_full['min_7'].unique())), duplicates='drop').cat.codes
df_feature_full['std_7'] = pd.qcut(df_feature_full['std_7'],
min(10, len(df_feature_full['std_7'].unique())), duplicates='drop').cat.codes
df_feature_full['var_7'] = pd.qcut(df_feature_full['var_7'],
min(10, len(df_feature_full['var_7'].unique())), duplicates='drop').cat.codes
df_feature_full['max_7'] = pd.qcut(df_feature_full['max_7'],
min(10, len(df_feature_full['max_7'].unique())), duplicates='drop').cat.codes
df_feature_full['sum_7'] = pd.qcut(df_feature_full['sum_7'],
min(10, len(df_feature_full['sum_7'].unique())), duplicates='drop').cat.codes
df_feature_full['min_3'] = pd.qcut(df_feature_full['min_3'],
min(10, len(df_feature_full['min_3'].unique())), duplicates='drop').cat.codes
df_feature_full['std_3'] = pd.qcut(df_feature_full['std_3'],
min(10, len(df_feature_full['std_3'].unique())), duplicates='drop').cat.codes
df_feature_full['var_3'] = pd.qcut(df_feature_full['var_3'],
min(10, len(df_feature_full['var_3'].unique())), duplicates='drop').cat.codes
df_feature_full['max_3'] = pd.qcut(df_feature_full['max_3'],
min(10, len(df_feature_full['max_3'].unique())), duplicates='drop').cat.codes
df_feature_full['sum_3'] = pd.qcut(df_feature_full['sum_3'],
min(10, len(df_feature_full['sum_3'].unique())), duplicates='drop').cat.codes
# print(df_feature_full.head)
return df_feature_full
if __name__ == '__main__':
df_feature_full = file_operation.read_feature_full()
df_feature_full = binner_engine(df_feature_full)
file_operation.write_feature_full(df_feature_full)
s1_result = pd.Series([])
s2_result = pd.Series([])
s3_result = pd.Series([])
for goodsn in goodsn_list:
for store_id in store_ids:
df_goods = df_feature_full[
(df_feature_full['storeid'] == store_id)
& (df_feature_full['goodscode'] == goodsn)]
if len(df_goods.index) < 2 * 7:
continue
y = [v for i, v in df_goods['saleqty'].items()]
s1 = holt_winters_first_order_ewma(y, 0.3)
s2 = holt_winters_second_order_ewma(y, 0.3, 0.3)
s3 = triple_exponential_smoothing(y, 7, 0.3, 0.3, 0.1)
s1_result = pd.concat(
[s1_result, pd.Series(s1, index=df_goods.index)])
s2_result = pd.concat(
[s2_result, pd.Series(s2, index=df_goods.index)])
s3_result = pd.concat(
[s3_result, pd.Series(s3, index=df_goods.index)])
df_feature_full['smoothing1'] = s1_result
df_feature_full['smoothing2'] = s2_result
df_feature_full['smoothing3'] = s3_result
return df_feature_full
if __name__ == '__main__':
df_sale_feature = file_operation.read_feature_full()
df_sale_feature = smoothing(df_sale_feature)
file_operation.write_feature_full(df_sale_feature)
