Pandas - - - DataFrame 用法

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/jiaoyangdetian/article/details/81056410

import pandas as pd
import numpy as np

def pandasWork1():  # DataFrame 初始化，与数据的获取

    one = np.array(['name0', 'name1', 'name2', 'name3', 'name4', 'name5'])
    two = list([[1, 1, 1], [1, 0, 1], [0, 0, 0], [1, 0, 1], [0, 1, 0], [1, 1, 0]])
    three = list([[2, 4, 6], [0, 5, 9], [8, 3, 2], [4, 5, 9], [1, 2, 9], [2, 8, 0]])
    four = list([[0.1, 0.2, 0.3], [0.1, 0.2, 0.7], [0.1, 0.4, 0.3], [0.1, 0.9, 0.3], [0.2, 0.2, 0.3], [0.1, 0.5, 0.3]])

    dataFrame = pd.DataFrame({'name': one, 'lookCase': two, 'lookTimes': three, 'weightTimes': four
                              })  # 注：这里的one，two，three，four都是list()类型，np.array需要注明dtype
    print('dataFrame=', dataFrame)

    names = np.array(dataFrame['name'])
    print('names one=', type(names))


    return

def pandasWork2(): # 初始化，指定索引内容

    keys = list(['one', 'two', 'three', 'four'])
    values = list(['version', 'alisa', 'jack', 'joy'])
    frame1 = pd.DataFrame(values, index= keys)
    print('frame1=', frame1)

    return

def pandasWork3(): # 几个字典类型的源数据，组合为一个DataFrame

    dict1 = {'name1' : 'alisa', 'name2' : 'jack', 'name3' : 'Sam', 'name4' : 'Jason'}  # 字典，可以作为一种源数据
    dict2 = {'name1' : 18, 'name2' : 19, 'name3' : 20, 'name4' : 21}

    pop = {'nmaes' : dict1, 'age' : dict2}

    frame = pd.DataFrame(pop)
    print('frame=', frame)

    return

def pandasWork4(): # 指定索引顺序初始化

    # 建立一个一维的，指定索引值，指定title的dataframe
    keys = list(['one', 'two', 'three', 'four'])
    values = list(['version', 'alisa', 'jack', 'joy'])
    title = list(['name'])
    frame = pd.DataFrame(values, index=keys,columns= title)
    print('frame=', frame)

    # 建立一个多维的，指定索引值，指定title即表头的顺序的dataframe
    one = np.array(['version', 'alisa', 'jack', 'joy'])
    one = one.reshape(len(one), 1) # 首先要不数据转为列
    two = np.array([100, 200, 300, 400])
    two = two.reshape(len(two), 1)
    data = np.hstack((one, two))
    print('data=', data.shape)
    data = data.tolist()
    print('list data=', data)
    title1 = list(['name', 'number'])
    frame1 = pd.DataFrame(data, index= keys, columns=title1)
    print('frame1=', frame1)

    return

#pandasWork1()  # DataFrame 初始化，与数据的获取
#pandasWork2()  # 初始化，指定索引内容
#pandasWork3() # 几个字典类型的源数据，组合为一个DataFrame
#pandasWork4() # 指定索引顺序初始化