想整理一下存读取函数,方便以后直接调用。
这段代码非常好用,这个函数直接把各种格式文件给汇总了
def readDataFile(readPath): # readPath: 数据文件的地址和文件名
try:
if (readPath[-4:] == ".csv"):
dfFile = pd.read_csv(readPath, header=0, sep=",") # 间隔符为逗号,首行为标题行
# dfFile = pd.read_csv(filePath, header=None, sep=",") # sep: 间隔符,无标题行
elif (readPath[-4:] == ".xls") or (readPath[-5:] == ".xlsx"): # sheet_name 默认为 0
dfFile = pd.read_excel(readPath,header=0) # 首行为标题行
# dfFile = pd.read_excel(filePath, header=None) # 无标题行
elif (readPath[-4:] == ".dat"): # sep: 间隔符,header:首行是否为标题行
dfFile = pd.read_table(readPath, sep=" ", header=0) # 间隔符为空格,首行为标题行
# dfFile = pd.read_table(filePath,sep=",",header=None) # 间隔符为逗号,无标题行
else:
print("不支持的文件格式。")
except Exception as e:
print("读取数据文件失败:{}".format(str(e)))
return
return dfFile
kind_num_dict={1:0,2:0,3:0,4:2}
mid = pd.DataFrame(list(kind_num_dict.items()))
mid.to_csv('./p1_不同单品累加求和.csv', header=False, index=False)
xlsx_list=[{'日期':'2020-07-01','值':35},{'日期':'2020-07-02','值':31},{'日期':'2020-07-03','值':54}]
import pandas as pd
#定义一个字典
#将字典格式化为DataFrame数据
data = pd.DataFrame(xlsx_list)
#将数据写入Excel中
data.to_excel('test.xlsx')