pip install skope-rules

from sklearn.datasets import load_iris
from skrules import SkopeRules

dataset = load_iris()
feature_names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']
clf = SkopeRules(max_depth_duplicatinotallow=2,
                 n_estimators=30,
                 precision_min=0.3,
                 recall_min=0.1,
                 feature_names=feature_names)

for idx, species in enumerate(dataset.target_names):
    X, y = dataset.data, dataset.target
    clf.fit(X, y == idx)
    rules = clf.rules_[0:3]
    print("Rules for iris", species)
    for rule in rules:
        print(rule)
    print()
    print(20*'=')
    print()

import six
import sys
sys.modules['sklearn.externals.six'] = six
import mlrose

from sklearn.datasets import load_boston
from sklearn.metrics import precision_recall_curve
from matplotlib import pyplot as plt
from skrules import SkopeRules

dataset = load_boston()
clf = SkopeRules(max_depth_duplicatinotallow=None,
                 n_estimators=30,
                 precision_min=0.2,
                 recall_min=0.01,
                 feature_names=dataset.feature_names)

X, y = dataset.data, dataset.target > 25
X_train, y_train = X[:len(y)//2], y[:len(y)//2]
X_test, y_test = X[len(y)//2:], y[len(y)//2:]
clf.fit(X_train, y_train)
y_score = clf.score_top_rules(X_test) # Get a risk score for each test example
precision, recall, _ = precision_recall_curve(y_test, y_score)
plt.plot(recall, precision)
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Precision Recall curve')
plt.show()

# Import skope-rules
from skrules import SkopeRules

# Import librairies
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
from sklearn.metrics import roc_curve, precision_recall_curve
from matplotlib import cm
import numpy as np
from sklearn.metrics import confusion_matrix
from IPython.display import display

# Import Titanic data
data = pd.read_csv('../data/titanic-train.csv')

# 刪除年齡缺失的行
data = data.query('Age == Age')
# 為變量Sex創(chuàng)建編碼值
data['isFemale'] = (data['Sex'] == 'female') * 1
# 未變量Embarked創(chuàng)建編碼值
data = pd.concat(
    [data,
    pd.get_dummies(data.loc[:,'Embarked'], 
                   dummy_na=False, 
                   prefix='Embarked', 
                   prefix_sep='_')],
    axis=1
)
# 刪除沒有使用的變量
data = data.drop(['Name', 'Ticket', 'Cabin', 
                  'PassengerId', 'Sex', 'Embarked'], 
                 axis = 1)
# 創(chuàng)建訓(xùn)練及測試集
X_train, X_test, y_train, y_test = train_test_split(
    data.drop(['Survived'], axis=1), 
    data['Survived'], 
    test_size=0.25, random_state=42)
feature_names = X_train.columns

print('Column names are: ' + ' '.join(feature_names.tolist())+'.')
print('Shape of training set is: ' + str(X_train.shape) + '.')

Column names are: Pclass Age SibSp Parch Fare
isFemale Embarked_C Embarked_Q Embarked_S.
Shape of training set is: (535, 9).

# 訓(xùn)練一個梯度提升分類器，用于基準(zhǔn)測試
gradient_boost_clf = GradientBoostingClassifier(random_state=42, n_estimators=30, max_depth = 5)
gradient_boost_clf.fit(X_train, y_train)

# 訓(xùn)練一個隨機森林分類器，用于基準(zhǔn)測試
random_forest_clf = RandomForestClassifier(random_state=42, n_estimators=30, max_depth = 5)
random_forest_clf.fit(X_train, y_train)

# 訓(xùn)練一個決策樹分類器，用于基準(zhǔn)測試
decision_tree_clf = DecisionTreeClassifier(random_state=42, max_depth = 5)
decision_tree_clf.fit(X_train, y_train)

# 訓(xùn)練一個 skope-rules-boosting 分類器
skope_rules_clf = SkopeRules(feature_names=feature_names, random_state=42, n_estimators=30,
                               recall_min=0.05, precision_min=0.9,
                               max_samples=0.7,
                               max_depth_duplicatinotallow= 4, max_depth = 5)
skope_rules_clf.fit(X_train, y_train)


# 計算預(yù)測分?jǐn)?shù)
gradient_boost_scoring = gradient_boost_clf.predict_proba(X_test)[:, 1]
random_forest_scoring = random_forest_clf.predict_proba(X_test)[:, 1]
decision_tree_scoring = decision_tree_clf.predict_proba(X_test)[:, 1]

skope_rules_scoring = skope_rules_clf.score_top_rules(X_test)

# 獲得創(chuàng)建的生存規(guī)則的數(shù)量
print("用SkopeRules建立了" + str(len(skope_rules_clf.rules_)) + "條規(guī)則\n")

# 打印這些規(guī)則
rules_explanations = [
 "3歲以下和37歲以下，在頭等艙或二等艙的女性。"
    "3歲以上乘坐頭等艙或二等艙，支付超過26歐元的女性。"
 "坐一等艙或二等艙，支付超過29歐元的女性。"
 "年齡在39歲以上，在頭等艙或二等艙的女性。"
]
print('其中表現(xiàn)最好的4條 "泰坦尼克號生存規(guī)則" 如下所示：/n')
for i_rule, rule in enumerate(skope_rules_clf.rules_[:4])
    print(rule[0])
    print('->'+rules_explanations[i_rule]+ '\n')

用SkopeRules建立了9條規(guī)則。

其中表現(xiàn)最好的4條 "泰坦尼克號生存規(guī)則" 如下所示：

Age <= 37.0 and Age > 2.5 
and Pclass <= 2.5 and isFemale > 0.5  
-> 3歲以下和37歲以下，在頭等艙或二等艙的女性。

Age > 2.5 and Fare > 26.125 
and Pclass <= 2.5 and isFemale > 0.5  
-> 3歲以上乘坐頭等艙或二等艙，支付超過26歐元的女性。

Fare > 29.356250762939453 
and Pclass <= 2.5 and isFemale > 0.5  
-> 坐一等艙或二等艙，支付超過29歐元的女性。

Age > 38.5 and Pclass <= 2.5 
and isFemale > 0.5  
-> 年齡在39歲以上，在頭等艙或二等艙的女性。

def compute_y_pred_from_query(X, rule):
    score = np.zeros(X.shape[0])
    X = X.reset_index(drop=True)
    score[list(X.query(rule).index)] = 1
    return(score)

def compute_performances_from_y_pred(y_true, y_pred, index_name='default_index'):
    df = pd.DataFrame(data=
        {
            'precision':[sum(y_true * y_pred)/sum(y_pred)],
            'recall':[sum(y_true * y_pred)/sum(y_true)]
        },
        index=[index_name],
        columns=['precision', 'recall']
    )
    return(df)

def compute_train_test_query_performances(X_train, y_train, X_test, y_test, rule):
    
    y_train_pred = compute_y_pred_from_query(X_train, rule)
    y_test_pred = compute_y_pred_from_query(X_test, rule)
    
    performances = None
    performances = pd.concat([
        performances,
        compute_performances_from_y_pred(y_train, y_train_pred, 'train_set')],
        axis=0)
    performances = pd.concat([
        performances,
        compute_performances_from_y_pred(y_test, y_test_pred, 'test_set')],
        axis=0)
            
    return(performances)


print('Precision = 0.96 表示規(guī)則確定的96%的人是幸存者。')
print('Recall = 0.12 表示規(guī)則識別的幸存者占幸存者總數(shù)的12%\n')

for i in range(4):
    print('Rule '+str(i+1)+':')
    display(compute_train_test_query_performances(X_train, y_train,
                                                  X_test, y_test,
                                                  skope_rules_clf.rules_[i][0])
           )

Precision = 0.96 表示規(guī)則確定的96%的人是幸存者。
Recall = 0.12 表示規(guī)則識別的幸存者占幸存者總數(shù)的12%。

def plot_titanic_scores(y_true, scores_with_line=[], scores_with_points=[],
                        labels_with_line=['Gradient Boosting', 'Random Forest', 'Decision Tree'],
                        labels_with_points=['skope-rules']):
    gradient = np.linspace(0, 1, 10)
    color_list = [ cm.tab10(x) for x in gradient ]

    fig, axes = plt.subplots(1, 2, figsize=(12, 5),
                         sharex=True, sharey=True)
    ax = axes[0]
    n_line = 0
    for i_score, score in enumerate(scores_with_line):
        n_line = n_line + 1
        fpr, tpr, _ = roc_curve(y_true, score)
        ax.plot(fpr, tpr, linestyle='-.', c=color_list[i_score], lw=1, label=labels_with_line[i_score])
    for i_score, score in enumerate(scores_with_points):
        fpr, tpr, _ = roc_curve(y_true, score)
        ax.scatter(fpr[:-1], tpr[:-1], c=color_list[n_line + i_score], s=10, label=labels_with_points[i_score])
    ax.set_title("ROC", fnotallow=20)
    ax.set_xlabel('False Positive Rate', fnotallow=18)
    ax.set_ylabel('True Positive Rate (Recall)', fnotallow=18)
    ax.legend(loc='lower center', fnotallow=8)

    ax = axes[1]
    n_line = 0
    for i_score, score in enumerate(scores_with_line):
        n_line = n_line + 1
        precision, recall, _ = precision_recall_curve(y_true, score)
        ax.step(recall, precision, linestyle='-.', c=color_list[i_score], lw=1, where='post', label=labels_with_line[i_score])
    for i_score, score in enumerate(scores_with_points):
        precision, recall, _ = precision_recall_curve(y_true, score)
        ax.scatter(recall, precision, c=color_list[n_line + i_score], s=10, label=labels_with_points[i_score])
    ax.set_title("Precision-Recall", fnotallow=20)
    ax.set_xlabel('Recall (True Positive Rate)', fnotallow=18)
    ax.set_ylabel('Precision', fnotallow=18)
    ax.legend(loc='lower center', fnotallow=8)
    plt.show()
    
plot_titanic_scores(y_test,
                    scores_with_line=[gradient_boost_scoring, random_forest_scoring, decision_tree_scoring],
                    scores_with_points=[skope_rules_scoring]
                   )

n_rule_chosen = 4
y_pred = skope_rules_clf.predict_top_rules(X_test, n_rule_chosen)

print('The performances reached with '+str(n_rule_chosen)+' discovered rules are the following:')
compute_performances_from_y_pred(y_test, y_pred, 'test_set')