numpy/matplotlib/pandas

pandas

DataFrame

• 数据框化

import pandas as pd
from pandas import Series, DataFrame

data = {"name":["yahoo","google","facebook"], "marks":[200,400,800], "price":[9, 3, 7]}
f1 = DataFrame(data)
print(f1)
   marks      name  price
0    200     yahoo      9
1    400    google      3
2    800  facebook      7

• 添加索引

# 按指定顺序排列,并添加索引
f2 = DataFrame(data, columns = ['price', 'name', 'marks', 't'], index = ['a', 'b', 'c'])
print(f2)

   price      name  marks    t
a      9     yahoo    200  NaN
b      3    google    400  NaN
c      7  facebook    800  NaN
# 精准输出
print(f2['name']['a']) #yahoo

读取csv

import pandas as pd
from pandas import Series, DataFrame

marks = pd.read_csv('marks.csv')
print(marks)

读取excel

xlsx = pd.ExcelFile('.\marks.xlsx')
print(xlsx.sheet_names)
sheet_1 =xlsx.parse('Sheet1')
print(sheet_1)

['Sheet1', 'Sheet2', 'Sheet3', 'Sheet4', 'Sheet5', 'Sheet6']
       name  physics  python  math  english
0    Google      100     100    25       12
1  Facebook       45      54    44       88
2   Twitter       54      76    13       91
3     Yahoo       54     452    26      100

numpy

import numpy as np
x = [12,4,2,4,23,121]
y = [32,21,223,43,12,55]
nx = np.array(x)
ny = np.array(y)
print(nx/ny**2)
#数据筛选就这么简单
print(nx[nx>12])#[ 23 121]

# 二维数组
x = [12,43,23,42,23,11]
y = [32,21,23,43,12,55]

np_2d = np.array([x,y])
print(np_2d)
# 输出个坐标值
print(np_2d[0,1])
# 输出第二行
print(np_2d[1])
# 切片输出（含前不含后）
print(np_2d[:,1:3])
print(np_2d[1:,1:2])