def loadData(data_dir, stock_index):
df1 = pd.read_csv(
os.path.join(data_dir, stock_index, stock_index + "_2020_3.csv"))
df2 = pd.read_csv(
os.path.join(data_dir, stock_index, stock_index + "_2020_4.csv"))
df1 = pd.concat([df1, df2])
df1.columns = setColname().day_history_wangyi()
return df1
def loadData():
data_dir = data_dict.get("JiGouDiaoYan")
tmp_data_dir = tmp_data_dict.get("JiGouDiaoYan")
cols = setColname().jigoudiaoyan()
data_file = os.path.join(tmp_data_dir,"all_JiGouDiaoYan.csv")
df = pd.read_csv(data_file, \
error_bad_lines=False,header=None,sep=",")
df.columns = cols
df.to_csv(data_file,index=0)
return df
import pandas as pd from davidyu_cfg import * from functions.colNames import setColname data_dir = "day_history_wangyi" file_in = os.path.join(tmp_data_dict.get(data_dir), data_dir + ".csv") #data_file = os.path.join(file_in,header=None) df1 = pd.read_csv(file_in, header=None) df1 = df1.drop_duplicates() df1.columns = setColname().day_history_wangyi() df2 = df1[df1["stock_date"] >= "1997-01-01"] df2.to_csv(file_in, index=0)
from davidyu_cfg import *
from functions.data_dir import data_dict, stk_index_list, create_dir_if_not_exist
from functions.colNames import setColname
data_file = os.path.join(tmp_data_dict.get("JiGouDiaoYan"), "jigoudiaoyan.csv")
df1 = pd.read_csv(data_file, error_bad_lines=False)
cols = setColname().jigoudiaoyan()
df1.columns = cols
df1.rename(columns={"date": "stock_date"}, inplace=True)
df2 = df1[df1[df1.columns[3]] != df1.columns[3]]
df2 = df2[df2["ChangePercent"] != "stock_date"]
df2.to_csv(data_file, index=0, header=None)
from davidyu_cfg import *
from functions.data_dir import *
from functions.colNames import setColname
data_dir = tmp_data_dict.get("bankuai")
data_file = os.path.join(data_dir, "bankuai.csv")
df1 = pd.read_csv(data_file)
df1.columns = setColname().bankuai()
df1.to_csv(data_file, index=0, header=None)
return self
def reset_columns(self, sum_col_list):
self.SUM_COLUMNS = sum_col_list
return self
if __name__ == '__main__':
now_date, now_date_time = get_the_datetime(
) ## the now_date is like "2019_11_08"
now_date = "2020_06_12"
dir_dadan = data_dict.get("DADAN")
data_dir = os.path.join(dir_dadan, now_date)
print(data_dir)
df1 = combine_csv_in_folder(data_dir)
df1.columns = setColname().DADAN()
#aa = DaDanAna(df1).df_out
#aa = DaDanAna(df1).max_min().dadan_diff_stat().df_out
#print(aa.head(10))
'''
dadan sale total money
'''
df_merge = DaDanAna(df1).dadan_diff_stat()
df_merge1 = df_merge.df_out
df_merge.dadan_diff_stat_print()
#print(df_merge1.head(50))
#print(df_merge1.tail(30))
#df_merge2 = df_merge1[df_merge1.sale_num.isna()]
#df_merge3 = df_merge2.sort_values("buy_num",ascending=False)
#df1.to_csv("DADAN_sample.csv",index=0)