机器学习 三剑客

numpy

import numpy as np
# data = np.array([[1,2,3,4,5,6]])
# print(type(data)) # 查看类型
# print(data)
# print(data.ndim) # 查看高维数组的维度
# print(data.shape) # 查看高维数组的形状
# print(data.reshape(2,3)) # 改变数组形状的

 

data = np.arange(2,10,2) # 生成区间数组
data = np.array([data,data]) # 用一维度组合成2维度

data = np.arange(30)
# 转成三维
data = np.array([[data,data,data]])
print(data.shape)
print(data)

# data = np.linspace(1,9,10) # 生成区间数，均分, 包括首尾
# print(data)
# print(np.sum(data)) # 和
# print(np.max(data)) # 最大值
# print(np.min(data)) # 最小值
# print(np.mean(data))# 平均值
# print(np.std(data)) # 标准差
# print(np.var(data)) # 方差

 

# 数据类型的转换
# data = data.tolist() # tolist() 将bdarray转成list
# print(data)
# data = np.array([1,2,3,4]) # list转成ndarray
# print(data)

 

 

pandas

 

import pandas as pd
import numpy as np
# 数据类型：series 一维，datafram二维
data = pd.Series([1,2,3,4,5,6,7,8,9,10,11])
# data.head() # 默认取前5行
# data.tail() # 默认取后5行
# print(data[2:7]) # 切片取值

df = pd.DataFrame([[1,2,3,4,5],[6,7,8,9,10]],columns=['a','b','c','d','e'],index=['A','B'])
print(df)
# print(df.loc['B']) # 按照行标签取
# print(df.iloc[0]) # 按照行索引取

print(np.sum(df)) # 默认每列的和
print(np.sum(df,axis=1)) # axis=1：按行，axis=0：按列(默认)

转载于:https://www.cnblogs.com/txb1999/p/10788948.html