Python数据分析与机器学习-scikit-learn模型建立与评估

源码下载：

http://download.csdn.net/download/adam_zs/10218906

'''线性回归  做回归
预测车每加仑油能跑多远'''

import pandas as pd
import matplotlib.pyplot as plt

pd.set_option('display.height', 9999)
pd.set_option('display.max_rows', 9999)
pd.set_option('display.max_columns', 9999)
pd.set_option('display.width', 9999)

columns = ["mpg", "cylinders", "displacement", "horsepower", "weight", "acceleration", "model year", "origin",
           "car name"]
cars = pd.read_table("auto-mpg.data", delim_whitespace=True, names=columns)
'''
    mpg  cylinders  displacement horsepower  weight  acceleration  model year  origin                   car name
0  18.0          8         307.0      130.0  3504.0          12.0          70       1  chevrolet chevelle malibu
1  15.0          8         350.0      165.0  3693.0          11.5          70       1          buick skylark 320
2  18.0          8         318.0      150.0  3436.0          11.0          70       1         plymouth satellite
3  16.0          8         304.0      150.0  3433.0          12.0          70       1              amc rebel sst
4  17.0          8         302.0      140.0  3449.0          10.5          70       1                ford torino
'''
# fig = plt.figure()
# ax1 = fig.add_subplot(211)
# ax2 = fig.add_subplot(212)
# cars.plot("weight", "mpg", kind="scatter", ax=ax1)
# cars.plot("acceleration", "mpg", kind="scatter", ax=ax2)
# plt.show()

from sklearn.linear_model import LinearRegression

lr = LinearRegression()
lr.fit(cars[['weight']], cars['mpg'])
predictions = lr.predict(cars[['weight']])

plt.scatter(cars['weight'], cars['mpg'], c='B')
plt.scatter(cars['weight'], predictions, c='R')
plt.show()

from sklearn.metrics import mean_squared_error  # 均方误差函数

print(mean_squared_error(cars["mpg"], predictions))

import pandas as pd
import matplotlib.pyplot as plt

'''逻辑回归-做分类'''
# 申请学校 数据
admissions = pd.read_csv("admissions.csv")
'''
   admit       gpa         gre
0      0  3.177277  594.102992
1      0  3.412655  631.528607
2      0  2.728097  553.714399
3      0  3.093559  551.089985
4      0  3.141923  537.184894
'''

from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression

linear_regression = LinearRegression()
linear_regression.fit(admissions[["gpa"]], admissions["admit"])
linear_predict = linear_regression.predict(admissions[["gpa"]])

logistic_regression = LogisticRegression()
logistic_regression.fit(admissions[["gpa"]], admissions["admit"])
logistic_predict = logistic_regression.predict(admissions[["gpa"]])  # predict得到具体的分类

logistic_predict_proba = logistic_regression.predict_proba(admissions[["gpa"]])  # predict_proba得到分类的概率

plt.scatter(admissions["gpa"], linear_predict, c="R")
plt.scatter(admissions["gpa"], logistic_predict, c="B")
plt.scatter(admissions["gpa"], logistic_predict_proba[:, 1], c="G")
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression

admissions = pd.read_csv("admissions.csv")
'''
   admit       gpa         gre
0      0  3.177277  594.102992
1      0  3.412655  631.528607
2      0  2.728097  553.714399
3      0  3.093559  551.089985
4      0  3.141923  537.184894
'''
lr = LogisticRegression()
lr.fit(admissions[["gpa"]], admissions["admit"])
admissions["predicted_label"] = lr.predict(admissions[["gpa"]])
# print(admissions["predicted_label"].value_counts())
# 精度预测  预测正确的/总数
matches = admissions["predicted_label"] == admissions["admit"]
admissions_correct = admissions[matches]
# print(len(admissions_correct) / len(admissions))

'''交叉验证'''

from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
import pandas as pd

admissions = pd.read_csv("admissions.csv")
'''
   admit       gpa         gre
0      0  3.177277  594.102992
1      0  3.412655  631.528607
2      0  2.728097  553.714399
3      0  3.093559  551.089985
4      0  3.141923  537.184894
'''
lr = LogisticRegression()
kf = KFold(n_splits=5, shuffle=True, random_state=10)
accuracies = cross_val_score(lr, admissions[['gpa']], admissions['admit'], cv=kf)
average_accuracy = sum(accuracies) / len(accuracies)
print(accuracies)
print(average_accuracy)

import pandas as pd
import matplotlib.pyplot as plt

'''多分类问题'''
pd.set_option('display.height', 9999)
pd.set_option('display.max_rows', 9999)
pd.set_option('display.max_columns', 9999)
pd.set_option('display.width', 9999)

columns = ["mpg", "cylinders", "displacement", "horsepower", "weight", "acceleration", "year", "origin", "car name"]
cars = pd.read_table("auto-mpg.data", delim_whitespace=True, names=columns)
'''
      mpg  cylinders  displacement horsepower  weight  acceleration  year  origin                              car name
0    18.0          8         307.0      130.0  3504.0          12.0    70       1             chevrolet chevelle malibu
1    15.0          8         350.0      165.0  3693.0          11.5    70       1                     buick skylark 320
2    18.0          8         318.0      150.0  3436.0          11.0    70       1                    plymouth satellite
3    16.0          8         304.0      150.0  3433.0          12.0    70       1                         amc rebel sst
'''
# get_dummies把气缸数量转换为列属性
dummy_cylinders = pd.get_dummies(cars['cylinders'], prefix='cyl')
dummy_years = pd.get_dummies(cars['year'], prefix='year')
cars = cars.drop("cylinders", axis=1)
cars = cars.drop("year", axis=1)
cars = pd.concat([cars, dummy_cylinders], axis=1)
cars = pd.concat([cars, dummy_years], axis=1)
print(cars.head())