from datetime
import timedelta
from pandas
import DataFrame
from scipy
import stats
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
path =
'links_date.csv'
# Open original data
parse_dates = [
'start',
'end']
df = pd.read_csv(path, index_col=
'tmdbId', parse_dates=
parse_dates)
# Drop null data
df.dropna(inplace=
True)
# Fill null data
# df.fillna(0, inplace=True)
# Obtain hourly data
df[
'DELTATIME'] = df[
'end'] - df[
'start']
# Select column
df = df[df[
'DELTATIME'] == timedelta(hours=1
)]
# Drop column
df.drop(
'DELTATIME', axis=1, inplace=
True)
# Handle data
转载于:https://www.cnblogs.com/wangjingchn/p/7302504.html
相关资源：python数据分析pandas快速入门教程.pdf
