python进行数据抽取_python中的数据抽取

首先创建一个数据帧(使用随机数据)：import pandas as pd

import numpy as np

from datetime import datetime, timedelta

ab = pd.DataFrame()

ab["subjectID"] = np.random.randint(5, size=200)#random list of "subjects" from 0 to 4

ab["day_number"] = np.random.randint(50, size=200)#random list of "dates" from 0 to 50

ab['real_date'] = ab.day_number.apply(lambda d: datetime(2018, 1, 1) + timedelta(days=d)) #to simulate real dates

ab["score1"] = np.random.randint(200, size=200)#meant to simulate one measurement from one subject

ab["score2"] = np.random.randint(400, size=200)#meant to simulate a second measurement

min_day = ab.real_date.min()

ab = ab.groupby(['subjectID', 'real_date']).sum() #because some subjects have more than 1 score each day

print