机器学习：python实践 回归项目实例 学习记录

# 导入类库
import numpy as np
import pandas
from numpy import arange
from matplotlib import pyplot
from pandas import read_csv
from pandas import set_option
from pandas.plotting import scatter_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet
from sklearn.tree import DecisionTreeRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.ensemble import AdaBoostRegressor
from sklearn.metrics import mean_squared_error

# 2 导入数据
filename = 'chapter20/housing.csv'
names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'EAD',
         'TAX', 'PRTATIO', 'B', 'LSTAT', 'MEDV']
dataset = read_csv(filename, names=names, delim_whitespace=True)

# 3 理解数据
# 数据维度
print(dataset.shape)
print(dataset.dtypes)
# 查看最开始的30条记录
# pandas.set_option('display.line_width', 120)
print(dataset.head(30))

# 描述性统计信息
set_option('display.precision', 1)
print(dataset.describe())
# 关联关系
set_option('display.precision', 2)
print("相关性：")
print(dataset.corr(method='pearson'))

# 4 数据可视化
# 直方图
dataset.hist(sharex=False, sharey=False, xlabelsize=1, ylabelsize=1)
pyplot.show()
# 密度图
dataset.plot(kind='density', subplots=True, layout=(4,4), sharex=False,
             fontsize=1)
pyplot.show()

# 箱线图
dataset.plot(kind="box", subplots=True, layout=(4,4), sharex=False,
             sharey=False, fontsize=8)
pyplot.show()
# 散点矩阵图
scatter_matrix(dataset)
pyplot.show()

# 相关矩阵图
fig = pyplot.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(dataset.corr(), vmin=-1, vmax=1, interpolation='none')
fig.colorbar(cax)
ticks = np.arange(0, 14, 1)
ax.set_xticks(ticks)
ax.set_yticks(ticks)
ax.set_xticklabels(names)
ax.set_yticklabels(names)
pyplot.show()

# 分离数据集
array = dataset.values
X = array[:, 0:13]
Y = array[:, 13]
validation_size = 0.2
seed = 7
X_train, X_validation, Y_train, Y_validation = train_test_split(X, Y, test_size=validation_size,
                                                                random_state=seed)
# 6 评估算法
# 评估算法 -- 评估标准
num_folds = 10
seed = 7
scoring = 'neg_mean_squared_error'

# 6.1 评估算法 - baseline
models = {}
models['LR'] = LinearRegression()
models['LASSO'] = Lasso()
models['EN'] = ElasticNet()
models['KNN'] = KNeighborsRegressor()
models['CART'] = DecisionTreeRegressor()
models['SVM'] = SVR()

# 评估算法
results = []
for key in models:
    kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
    cv_result = cross_val_score(models[key], X_train, Y_train, cv=kfold,
                                scoring=scoring)
    results.append(cv_result)
    print('%s: %f (%f)' % (key, cv_result.mean(), cv_result.std()))
# 评估算法--箱线图
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()

# 6.2 评估算法--正态化数据

pipelines = {}
pipelines['ScalerLR'] = Pipeline([('Scaler', StandardScaler()), ('LR',
                                                                 LinearRegression())])
pipelines['ScalerLASSO'] = Pipeline([('Scaler', StandardScaler()), ('LASSO',
                                                                    Lasso())])
pipelines['ScalerEN'] = Pipeline([('Scaler',
                                   StandardScaler()), ('EN', ElasticNet())])
pipelines['ScalerKNN'] = Pipeline([('Scaler',
                                    StandardScaler()), ('KNN', KNeighborsRegressor())])
pipelines['ScalerCART'] = Pipeline([('Scaler',
                                     StandardScaler()), ('CART', DecisionTreeRegressor())])
pipelines['ScalerSVM'] = Pipeline([('Scaler',
                                    StandardScaler()), ('SVM', SVR())])
results = []
for key in pipelines:
    kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
    cv_result = cross_val_score(pipelines[key], X_train, Y_train, cv=kfold,
                                scoring=scoring)
    results.append(cv_result)
    print('%s: %f(%f)' % (key, cv_result.mean(), cv_result.std()))
# 评估算法--箱线图
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()

# 7 调参改善算法--KNN
scaler = StandardScaler().fit(X_train)
rescaledX = scaler.transform(X_train)
param_grid = {'n_neighbors': [1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21]}
model = KNeighborsRegressor()
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
grid = GridSearchCV(estimator=model,
                    param_grid=param_grid, scoring=scoring, cv=kfold)
grid_results = grid.fit(X=rescaledX, y=Y_train)

print('最优：%s 使用%s' % (grid_results.best_score_, grid_results.best_params_))
cv_results = zip(grid_results.cv_results_['mean_test_score'],
                 grid_results.cv_results_['std_test_score'],
                 grid_results.cv_results_['params'])
for mean, std, param in cv_results:
    print('%f (%f) with %r' % (mean, std, param))

# 8 集成算法
ensembles = {}
ensembles['ScaledAB'] = Pipeline([('Scale', StandardScaler()),
                                  ('AB', AdaBoostRegressor())])
ensembles['ScaledAB-KNN'] = Pipeline(
    [('Scaler', StandardScaler()), ('ABKNN', AdaBoostRegressor(base_estimator=KNeighborsRegressor(n_neighbors=3)))])
ensembles['ScaledAB-LR'] = Pipeline([('Scaler',
                                      StandardScaler()), ('ABLR', AdaBoostRegressor(LinearRegression()))])
ensembles['ScaledRFR'] = Pipeline([('Scaler', StandardScaler()), ('RFR', RandomForestRegressor())])
ensembles['ScaledETR'] = Pipeline([('Scaler',
                                    StandardScaler()), ('ETR', ExtraTreesRegressor())])
ensembles['ScaledGBR'] = Pipeline([('Scaler', StandardScaler()), ('RBR', GradientBoostingRegressor())])

results = []
for key in ensembles:
    kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
    cv_result = cross_val_score(ensembles[key], X_train, Y_train, cv=kfold, scoring=scoring)
    results.append(cv_result)
    print('%s: %f (%f)' % (key, cv_result.mean(), cv_result.std()))

# 集成算法 -- 箱线图
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(ensembles.keys())
pyplot.show()

# 9 集成算法调参
caler = StandardScaler().fit(X_train)
rescaledX = scaler.transform(X_train)
param_grid = {'n_estimators': [10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900]}
model = GradientBoostingRegressor()
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
grid = GridSearchCV(estimator=model,
                    param_grid=param_grid, scoring=scoring, cv=kfold)
grid_result = grid.fit(X=rescaledX, y=Y_train)
print('最优: %s 使用%s' % (grid_result.best_score_,
                       grid_result.best_params_))

# 集成算法ET--调参
scaler = StandardScaler().fit(X_train)
rescaledX = scaler.transform(X_train)
param_grid = {'n_estimators': [5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100]}
model = ExtraTreesRegressor()
kfold = KFold(n_splits=num_folds, random_state=seed, shuffle=True)
grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring=scoring,
                    cv=kfold)
grid_result = grid.fit(X=rescaledX, y=Y_train)
print('最优: %s 使用%s' % (grid_result.best_score_, grid_result.best_params_))

# 10 确定最终模型
# 训练模型
caler = StandardScaler().fit(X_train)
rescaledX = scaler.transform(X_train)
gbr = ExtraTreesRegressor(n_estimators=80)
gbr.fit(X=rescaledX, y=Y_train)
# 评估算法模型
rescaledX_validation = scaler.transform(X_validation)
predictions = gbr.predict(rescaledX_validation)
print(mean_squared_error(Y_validation, predictions))