Question

我必须加入两个表并创建一个包含日期的表，但是我的代码很长，我相信我已经完成了很长的路。显然，这个只有22行。有没有其他方法和更短的方法来解决这个问题。这是问题

这是我的代码，我相信这很长，我认为有一个更短的方法来做到这一点。

import numpy as np
import pandas as pd
import datetime

#YOUR CODE GOES HERE#

def get_month(i):
    """this function returns the number of the month based on stringinput"""
    if i == "January":
        return 1
    elif i == "February":
        return 2
    elif i == "March":
        return 3
    elif i == "April":
        return 4
    elif i == "May":
        return 5
    elif i == "June":
        return 6
    elif i == "July":
        return 7
    elif i == "August":
        return 8
    elif i == "September":
        return 9
    elif i == "October":
        return 10
    elif i == "November":
        return 11
    elif i == "December":
        return 12

def get_reformatted_date(s):
    """this function reformats a datetime object to the output we're looking for"""
    return s.strftime("%d-%b-%y")


month_names = []
tab1 = pd.read_csv("data1.csv")
tab2 = pd.read_csv("data2.csv")
tab1_tweets = tab1['Tweet'].tolist()[::-1]
tab2_tweets = tab2['Tweet'].tolist()[::-1]
tab1_months = tab1['Month'].tolist()[::-1]
tab2_months = tab2['Month'].tolist()[::-1]
tab1_days = tab1['Day'].tolist()[::-1]
tab2_days = tab2['Day'].tolist()[::-1]
tab1_years = tab1['Year'].tolist()[::-1]
tab2_years = tab2['Year'].tolist()[::-1]
all_dates = []
all_tweets = []
tab1_count = 0
tab2_count = 0
for i in range(len(tab1_tweets) + len(tab2_tweets)):
    if(tab1_count < len(tab1_years) and tab2_count < len(tab2_years)):
        t1_date = datetime.date(tab1_years[tab1_count], tab1_months[tab1_count], tab1_days[tab1_count])
        t2_date = datetime.date(tab2_years[tab2_count], get_month(tab2_months[tab2_count]), tab2_days[tab2_count])
        if t1_date > t2_date:
            all_dates.append(t1_date)
            all_tweets.append(tab1_tweets[tab1_count])
            tab1_count += 1
        else:
            all_dates.append(t2_date)
            all_tweets.append(tab2_tweets[tab2_count])
            tab2_count += 1
    elif(tab2_count < len(tab2_years)):
        t2_date = datetime.date(tab2_years[tab2_count], get_month(tab2_months[tab2_count]), tab2_days[tab2_count])
        all_dates.append(t2_date)
        all_tweets.append(tab2_tweets[tab2_count])
        tab2_count += 1
    else:
        t1_date = datetime.date(tab1_years[tab1_count], tab1_months[tab1_count], tab1_days[tab1_count])
        all_dates.append(t1_date)
        all_tweets.append(tab1_tweets[tab1_count])
        tab1_count += 1

table_data = {'Date': all_dates, 'Tweet': all_tweets}
df = pd.DataFrame(table_data)
df['Date'] = df['Date'].apply(get_reformatted_date)
print(df)

data1.csv是

Tweet                 Month Day  Year
Hello World             6    2    2013
I want ice-cream!       7    23   2013
Friends will be friends 9    30   2017
Done with school        12   12   2017

data2.csv是

Month   Day Year    Hour    Tweet
January 2   2015    12  Happy New Year
March   21  2016    7   Today is my final
May     30  2017    23  Summer is about to begin
July    15  2018    11  Ocean is still cold

Answer 1

我认为你理论上可以在一行中完成这一切：

finaldf = (pd.concat([pd.read_csv('data1.csv',
                            parse_dates={'Date':['Year', 'Month', 'Day']}),
                      pd.read_csv('data2.csv',
                            parse_dates={'Date':['Year', 'Month', 'Day']})
                      [['Date', 'Tweet']]])
            .sort_values('Date', ascending=False))

但为了便于阅读，最好将其分成几行：

df1 = pd.read_csv('data1.csv', parse_dates={'Date':['Year', 'Month','Day']})
df2 = pd.read_csv('data2.csv', parse_dates={'Date':['Year', 'Month','Day']})

finaldf = (pd.concat([df1, df2[['Date', 'Tweet']]])
          .sort_values('Date', ascending=False))

我认为，对于您尝试做的事情，要阅读的主要内容是pandas read_csv的parse_dates参数和pd.concat来连接数据框< / p>

修改：为了按照示例输出中的格式获取日期，您可以使用Series.dt.strftime()在上面的代码后调用此日期：

finaldf['Date'] = finaldf['Date'].dt.strftime('%d-%b-%y')

pandas从两个表创建新表

1 个答案: