一文搞懂Python Sklearn库使用

from sklearn.preprocessing import LabelEncoder
encoder=LabelEncoder()
encoder.fit([1,3,2,6])
t=encoder.transform([1,6,6,2])
print(t)

from sklearn.preprocessing import OneHotEncoder
oneHot=OneHotEncoder()#声明一个编码器
oneHot.fit([[1],[2],[3],[4]])
print(oneHot.transform([[2],[3],[1],[4]]).toarray())

X_train,X_test, y_train, y_test =train_test_split(train_data,train_target,test_size=0.2, train_size=0.8,random_state=0)

from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
iris=load_iris()
train=iris.data
target=iris.target
# 避免过拟合，采用交叉验证，验证集占训练集20%，固定随机种子（random_state)
train_X,test_X, train_y, test_y = train_test_split(train,
                                                   target,
                                                   test_size = 0.2,
                                                   random_state = 0)
print(train_y.shape)

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
 
from sklearn.pipeline import Pipeline
#需要联网
df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data',
                 header=None)
                                 # Breast Cancer Wisconsin dataset
X, y = df.values[:, 2:], df.values[:, 1]
encoder = LabelEncoder()
y = encoder.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2, random_state=0)
pipe_lr = Pipeline([('sc', StandardScaler()),
                    ('pca', PCA(n_components=2)),
                    ('clf', LogisticRegression(random_state=1))
                    ])
pipe_lr.fit(X_train, y_train)
print('Test accuracy: %.3f' % pipe_lr.score(X_test, y_test))

anova_filter = SelectKBest(f_regression, k=5)
clf = svm.SVC(kernel='linear')
anova_svm = Pipeline([('anova', anova_filter), ('svc', clf)])

# conding :utf-8
from sklearn.linear_model import LogisticRegression
import numpy as np
 
x_train = np.array([[1, 2, 3],
                    [1, 3, 4],
                    [2, 1, 2],
                    [4, 5, 6],
                    [3, 5, 3],
                    [1, 7, 2]])
 
y_train = np.array([3, 3, 3, 2, 2, 2])
 
x_test = np.array([[2, 2, 2],
                   [3, 2, 6],
                   [1, 7, 4]])
 
clf = LogisticRegression()
clf.fit(x_train, y_train)
 
# 返回预测标签
print(clf.predict(x_test))
 
# 返回预测属于某标签的概率
print(clf.predict_proba(x_test))

import numpy as np
from sklearn.metrics import roc_curve
from sklearn.metrics import auc
y = np.array([1,0,2,2])
pred = np.array([0.1, 0.4, 0.35, 0.8])
fpr, tpr, thresholds = roc_curve(y, pred, pos_label=2)
print(tpr)
print(fpr)
print(thresholds)
print(auc(fpr, tpr))

model=Lasso()
alpha_can=np.logspace(-3,2,10)
np.set_printoptions(suppress=True)#设置打印选项
print("alpha_can=",alpha_can)
#cv :交叉验证参数，默认None 这里为5折交叉
# param_grid：值为字典或者列表，即需要最优化的参数的取值
lasso_model=GridSearchCV(model,param_grid={'alpha':alpha_can},cv=5)#得到最好的参数
lasso_model.fit(x_train,y_train)
print('超参数：\n',lasso_model.best_params_)
print("估计器\n",lasso_model.best_estimator_)

pipeline= Pipeline([("features", combined_features), ("svm", svm)])  
param_grid= dict(features__pca__n_components=[1, 2, 3],  
                  features__univ_select__k=[1,2],  
                  svm__C=[0.1, 1, 10])  
   
grid_search= GridSearchCV(pipeline, param_grid=param_grid, verbose=10)  
grid_search.fit(X,y)  
print(grid_search.best_estimator_) 

# coding=utf-8
# 统计训练集的 mean 和　std 信息
from sklearn.preprocessing import StandardScaler
import numpy as np
 
 
def test_algorithm():
    np.random.seed(123)
    print('use StandardScaler')
    # 注：shape of data: [n_samples, n_features]
    data = np.random.randn(3, 4)
    scaler = StandardScaler()
    scaler.fit(data)
    trans_data = scaler.transform(data)
    print('original data: ')
    print(data)
    print('transformed data: ')
    print(trans_data)
    print('scaler info: scaler.mean_: {}, scaler.var_: {}'.format(scaler.mean_, scaler.var_))
    print('\n')
 
    print('use numpy by self')
    mean = np.mean(data, axis=0)
    std = np.std(data, axis=0)
    var = std * std
    print('mean: {}, std: {}, var: {}'.format(mean, std, var))
    # numpy 的广播功能
    another_trans_data = data - mean
    # 注：是除以标准差
    another_trans_data = another_trans_data / std
    print('another_trans_data: ')
    print(another_trans_data)
 
 
if __name__ == '__main__':
    test_algorithm()

import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
 
path = r"activity_recognizer\1.csv"
# 数据在https://archive.ics.uci.edu/ml/datasets/Activity+Recognition+from+Single+Chest-Mounted+Accelerometer
df = pd.read_csv(path, header=None)
df.columns = ['index', 'x', 'y', 'z', 'activity']
 
knn = KNeighborsClassifier()
knn_params = {'n_neighbors': [3, 4, 5, 6]}
X = df[['x', 'y', 'z']]
y = df['activity']
 
from sklearn.preprocessing import PolynomialFeatures
 
poly = PolynomialFeatures(degree=2, include_bias=False, interaction_only=False)
X_ploly = poly.fit_transform(X)
X_ploly_df = pd.DataFrame(X_ploly, columns=poly.get_feature_names())
print(X_ploly_df.head())

import numpy as np
np.random.seed(10)
%matplotlib inline 
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import (RandomTreesEmbedding, RandomForestClassifier,
                              GradientBoostingClassifier)
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_curve,accuracy_score,recall_score
from sklearn.pipeline import make_pipeline
from sklearn.calibration import calibration_curve
import copy
print(__doc__)
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
 
# 数据
X, y = make_classification(n_samples=100000)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state = 4000)  # 对半分
X_train, X_train_lr, y_train, y_train_lr = train_test_split(X_train,
                                                            y_train,
                                                            test_size=0.2,random_state = 4000)
print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
 
def yLabel(y_pred):
    y_pred_f = copy.copy(y_pred)
    y_pred_f[y_pred_f>=0.5] = 1
    y_pred_f[y_pred_f<0.5] = 0
    return y_pred_f
 
def acc_recall(y_test, y_pred_rf):
    return {'accuracy': accuracy_score(y_test, yLabel(y_pred_rf)), \
            'recall': recall_score(y_test, yLabel(y_pred_rf))}

h = .02  # step size in the mesh
names = ["Nearest Neighbors", "Linear SVM", "RBF SVM",
         "Decision Tree", "Neural Net", "AdaBoost",
         "Naive Bayes", "QDA"]
# 去掉"Gaussian Process"，太耗时，是其他的300倍以上
 
classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    #GaussianProcessClassifier(1.0 * RBF(1.0)),
    DecisionTreeClassifier(max_depth=5),
    #RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    MLPClassifier(alpha=1),
    AdaBoostClassifier(),
    GaussianNB(),
    QuadraticDiscriminantAnalysis()]
 
predictEight = {}
for name, clf in zip(names, classifiers):
    predictEight[name] = {}
    predictEight[name]['prob_pos'],predictEight[name]['fpr_tpr'],predictEight[name]['acc_recall'] = [],[],[]
    predictEight[name]['importance'] = []
    print('\n --- Start Model : %s ----\n'%name)
    %time clf.fit(X_train, y_train)
    # 一些计算决策边界的模型 计算decision_function
    if hasattr(clf, "decision_function"):
        %time prob_pos = clf.decision_function(X_test)
        # # The confidence score for a sample is the signed distance of that sample to the hyperplane.
    else:
        %time prob_pos= clf.predict_proba(X_test)[:, 1]
        prob_pos = (prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())
        # 需要归一化
    predictEight[name]['prob_pos'] = prob_pos
 
    # 计算ROC、acc、recall
    predictEight[name]['fpr_tpr'] = roc_curve(y_test, prob_pos)[:2]
    predictEight[name]['acc_recall'] = acc_recall(y_test, prob_pos)  # 计算准确率与召回
 
    # 提取信息
    if hasattr(clf, "coef_"):
        predictEight[name]['importance'] = clf.coef_
    elif hasattr(clf, "feature_importances_"):
        predictEight[name]['importance'] = clf.feature_importances_
    elif hasattr(clf, "sigma_"):
        predictEight[name]['importance'] = clf.sigma_
        # variance of each feature per class 在朴素贝叶斯之中体现

'''
model 0 : lm
logistic
'''
print('LM 开始计算...')
lm = LogisticRegression()
%time lm.fit(X_train, y_train)
y_pred_lm = lm.predict_proba(X_test)[:, 1]
fpr_lm, tpr_lm, _ = roc_curve(y_test, y_pred_lm)
lm_ar = acc_recall(y_test, y_pred_lm)  # 计算准确率与召回
 
'''
model 1 : rt + lm
无监督变换 + lg
'''
# Unsupervised transformation based on totally random trees
print('随机森林编码+LM 开始计算...')
 
 
rt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator,
    random_state=0)
# 数据集的无监督变换到高维稀疏表示。
 
rt_lm = LogisticRegression()
pipeline = make_pipeline(rt, rt_lm)
%time pipeline.fit(X_train, y_train)
y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
rt_lm_ar = acc_recall(y_test, y_pred_rt)  # 计算准确率与召回
 
'''
model 2 : RF / RF+LM
'''
print('\n 随机森林系列 开始计算... ')
 
# Supervised transformation based on random forests
rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
rf_enc = OneHotEncoder()
rf_lm = LogisticRegression()
rf.fit(X_train, y_train)
rf_enc.fit(rf.apply(X_train))  # rf.apply(X_train)-(1310, 100)     X_train-(1310, 20)
# 用100棵树的信息作为X，载入做LM模型
%time rf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)
 
y_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]
fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
rf_lm_ar = acc_recall(y_test, y_pred_rf_lm)  # 计算准确率与召回
 
'''
model 2 : GRD / GRD + LM
'''
print('\n 梯度提升树系列 开始计算... ')
 
grd = GradientBoostingClassifier(n_estimators=n_estimator)
grd_enc = OneHotEncoder()
grd_lm = LogisticRegression()
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
%time grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
 
y_pred_grd_lm = grd_lm.predict_proba(
    grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
fpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)
grd_lm_ar = acc_recall(y_test, y_pred_grd_lm)  # 计算准确率与召回
 
# The gradient boosted model by itself
y_pred_grd = grd.predict_proba(X_test)[:, 1]
fpr_grd, tpr_grd, _ = roc_curve(y_test, y_pred_grd)
grd_ar = acc_recall(y_test, y_pred_grd)  # 计算准确率与召回
 
 
# The random forest model by itself
y_pred_rf = rf.predict_proba(X_test)[:, 1]
fpr_rf, tpr_rf, _ = roc_curve(y_test, y_pred_rf)
rf_ar = acc_recall(y_test, y_pred_rf)  # 计算准确率与召回

# 8款常规模型
for x,y in predictEight.items():
    print('\n ----- The Model  : %s , -----\n '%(x)  )
    print(predictEight[x]['acc_recall'])
 
# 树模型
names = ['LM','LM + RT','LM + RF','GBT + LM','GBT','RF']
ar_list = [lm_ar,rt_lm_ar,rf_lm_ar,grd_lm_ar,grd_ar,rf_ar]
for x,y in zip(names,ar_list):
    print('\n --- %s 准确率与召回为: ---- \n '%x,y)

# #############################################################################
# Plot calibration plots
names = ["Nearest Neighbors", "Linear SVM", "RBF SVM",
         "Decision Tree", "Neural Net", "AdaBoost",
         "Naive Bayes", "QDA"]
 
 
plt.figure(figsize=(15, 15))
ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)
ax2 = plt.subplot2grid((3, 1), (2, 0))
 
ax1.plot([0, 1], [0, 1], "k:", label="Perfectly calibrated")
for prob_pos, name in [[predictEight[n]['prob_pos'],n] for n in names] + [(y_pred_lm,'LM'),
                       (y_pred_rt,'RT + LM'),
                       (y_pred_rf_lm,'RF + LM'),
                       (y_pred_grd_lm,'GBT + LM'),
                       (y_pred_grd,'GBT'),
                       (y_pred_rf,'RF')]:
 
    prob_pos = (prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())
 
    fraction_of_positives, mean_predicted_value = calibration_curve(y_test, prob_pos, n_bins=10)
 
    ax1.plot(mean_predicted_value, fraction_of_positives, "s-",
             label="%s" % (name, ))
 
    ax2.hist(prob_pos, range=(0, 1), bins=10, label=name,
             histtype="step", lw=2)
 
ax1.set_ylabel("Fraction of positives")
ax1.set_ylim([-0.05, 1.05])
ax1.legend(loc="lower right")
ax1.set_title('Calibration plots  (reliability curve)')
 
ax2.set_xlabel("Mean predicted value")
ax2.set_ylabel("Count")
ax2.legend(loc="upper center", ncol=2)
 
plt.tight_layout()
plt.show()

# 重要性
print('\n -------- RadomFree importances ------------\n')
print(rf.feature_importances_)
print('\n -------- GradientBoosting importances ------------\n')
print(grd.feature_importances_)
print('\n -------- Logistic Coefficient  ------------\n')
lm.coef_ 
# 其他几款模型的特征选择
[[predictEight[n]['importance'],n] for n in names if predictEight[n]['importance'] != [] ]

plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr_lm, tpr_lm, label='LR')
plt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')
plt.plot(fpr_rf, tpr_rf, label='RF')
plt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')
plt.plot(fpr_grd, tpr_grd, label='GBT')
plt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')
# 8 款模型
for (fpr,tpr),name in [[predictEight[n]['fpr_tpr'],n] for n in names] :
    plt.plot(fpr, tpr, label=name)
 
 
plt.xlabel('False positive rate')
plt.ylabel('True positive rate')
plt.title('ROC curve')
plt.legend(loc='best')
plt.show()
 
plt.figure(2)
plt.xlim(0, 0.2)
plt.ylim(0.4, 1)     # ylim改变     # matt
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr_lm, tpr_lm, label='LR')
plt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')
plt.plot(fpr_rf, tpr_rf, label='RF')
plt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')
plt.plot(fpr_grd, tpr_grd, label='GBT')
plt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')
for (fpr,tpr),name in [[predictEight[n]['fpr_tpr'],n] for n in names] :
    plt.plot(fpr, tpr, label=name)
plt.xlabel('False positive rate')
plt.ylabel('True positive rate')
plt.title('ROC curve (zoomed in at top left)')
plt.legend(loc='best')
plt.show()