《封号码罗》数据分析与人工智能之sklearn模型评估和交叉表（十）

第一部分

import numpy as np
from sklearn.linear_model import LinearRegression
import sklearn.datasets as datasets

# 线性回归评价标准  糖尿病数据
diabetes = datasets.load_diabetes()
# print(datasets)
X = diabetes["data"]
y = diabetes["target"]
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# print(X_train.shape)
# 该数据有正有负，说明次数据被处理过。归一化
# print(X_train.std(axis=0))

lr = LinearRegression()
lr.fit(X_train, y_train)
y_ = lr.predict(X_test).round(0)

# R的平方，又叫决定系数评价
score = lr.score(X_test, y_test)
"""
The coefficient R^2 is defined as (1 - u/v), where u is the residual
sum of squares ((y_true - y_pred) ** 2).sum() and v is the total
sum of squares ((y_true - y_true.mean()) ** 2).sum().
"""

# print(y_, "\n", y_test)
# 下面这些都是评价指标
from sklearn.metrics import mean_absolute_error, mean_squared_log_error, mean_squared_error

ss = mean_absolute_error(y_test, y_)
print(ss)

第二部分

import numpy as np
import pandas as pd
from pandas import DataFrame, Series
from sklearn.neighbors import KNeighborsClassifier

cancer = pd.read_csv("./cancer.csv")

# 分析数据属性
# print(cancer.head())

# 获取数据  所有行，从第二列向后所有列
X = cancer.iloc[:, 2:]
y = cancer.Diagnosis  # 目标数据，Diagnosis是列名称

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# 声明算法
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
y_ = knn.predict(X_test).values

knn.score(X_test, y_test)  # 评估

accuracy_score(y_test, y_)  # 评估

# 交叉表 ，查看错误数据   margins自动汇总数据
# 对角线是正确的数据
pd.crosstab(index=y_test, columns=y_, rownames=["确诊"], colnames=["预测"], margins=True)

from sklearn.metrics import confusion_matrix

confusion_matrix(y_test, y_)  # 类似交叉表

from sklearn.metrics import classification_report

ss = classification_report(y_test, y_)  # 更多的参考评估指标

# ----------------------------------华丽分割线--------------------------------
# preprocessing 预处理 StandardScaler 归一化
from sklearn.preprocessing import StandardScaler

s = StandardScaler()
X2 = s.fit_transform(X)  # 对数据归一化
# X2[:5]  # 转化之后数据是一维数据了  0~1之间的数据
X2_train, X2_test, y2_train, y2_test = train_test_split(X2, y, test_size=0.2)
knn2 = KNeighborsClassifier()
knn2.fit(X2_train)
y_2 = knn2.predict(X2_test)
accuracy_score(y2_test, y_2)