Python DecisionTreeClassifier.apply方法代码示例

# 需要导入模块: from sklearn.tree import DecisionTreeClassifier [as 别名]
# 或者: from sklearn.tree.DecisionTreeClassifier import apply [as 别名]
def compute_new_features(X_train,y_train,X_test,y_test):
    classifier = DecisionTreeClassifier(max_leaf_nodes=50)
    classifier.fit(X_train,y_train)
    idx_train = classifier.apply(X_train)
    idx_train = idx_train.reshape([-1,1])
    enc = OneHotEncoder()
    enc.fit(idx_train)
    new_features_train = enc.transform(idx_train).toarray()
    
    idx_test = classifier.apply(X_test)
    idx_test = idx_test.reshape([-1,1])
    new_features_test = enc.transform(idx_test).toarray()

    return ([np.hstack([X_train,new_features_train]), np.hstack([X_test,new_features_test])])

# 需要导入模块: from sklearn.tree import DecisionTreeClassifier [as 别名]
# 或者: from sklearn.tree.DecisionTreeClassifier import apply [as 别名]
        print(
            "%snode=%s test node: go to node %s if X[:, %s] <= %ss else to "
            "node %s." % (node_depth[i] * "\t", i, children_left[i], feature[i], threshold[i], children_right[i])
        )
print()

# First let's retrieve the decision path of each sample. The decision_path
# method allows to retrieve the node indicator functions. A non zero element of
# indicator matrix at the position (i, j) indicates that the sample i goes
# through the node j.

node_indicator = estimator.decision_path(X_test)

# Similarly, we can also have the leaves ids reached by each sample.

leave_id = estimator.apply(X_test)

# Now, it's possible to get the tests that were used to predict a sample or
# a group of samples. First, let's make it for the sample.

sample_id = 0
node_index = node_indicator.indices[node_indicator.indptr[sample_id] : node_indicator.indptr[sample_id + 1]]

print("Rules used to predict sample %s: " % sample_id)
for node_id in node_index:
    if leave_id[sample_id] != node_id:
        continue

    if X_test[sample_id, feature[node_id]] <= threshold[node_id]:
        threshold_sign = "<="
    else:

# 需要导入模块: from sklearn.tree import DecisionTreeClassifier [as 别名]
# 或者: from sklearn.tree.DecisionTreeClassifier import apply [as 别名]
# -*- coding: utf-8 -*-

execfile('Original.py')
execfile('tfidf.py')

from sklearn.tree import DecisionTreeClassifier

s=DecisionTreeClassifier(max_depth=2, random_state=5)
s.fit(x,cuisine)
leaves=pd.Series(s.apply(x),name='leaves')
idk=pd.concat([cuisine,leaves],axis=1)
m=list(leaves.value_counts().index.values)
for y in m:
    print y
    print idk[leaves==y]['cuisine'].value_counts()
leaves.value_counts()


s2=DecisionTreeClassifier(max_depth=3, random_state=5)
s2.fit(x,cuisine)
leaves2=pd.Series(s2.apply(x),name='leaves')
idk=pd.concat([cuisine,leaves2],axis=1)
m=list(leaves2.value_counts().index.values)
for y in m:
    print y
    print idk[leaves2==y]['cuisine'].value_counts()
leaves2.value_counts()


s3=DecisionTreeClassifier(max_leaf_nodes=8, random_state=5,criterion='entropy')
s3.fit(x,cuisine)

# 需要导入模块: from sklearn.tree import DecisionTreeClassifier [as 别名]
# 或者: from sklearn.tree.DecisionTreeClassifier import apply [as 别名]
        #divide each column over sum of rows
        df_new=df.div(df.sum(axis=0),axis='columns').fillna(0)
    return df_new

def hmwrapper(cm,filename):
    h=heatmap(cm).get_figure()
    ax=h.add_subplot(111)
    ax.set_xlabel('Predictions')
    h.tight_layout()
    h.set_size_inches(8,5.5)
    h.savefig(filename,bbox_inches='tight',dpi=100)

#fitting/examining tree
s2=DecisionTreeClassifier(max_leaf_nodes=10, min_samples_leaf=500, random_state=5)
s2.fit(x,cuisine)
leaves2=pd.Series(s2.apply(x),name='leaves')
idk=pd.concat([cuisine,leaves2],axis=1)
m=list(leaves2.value_counts().index.values) #[3, 6, 10, 4, 7, 13, 11, 14]
for y in m:
    print y
    print idk[leaves2==y]['cuisine'].value_counts()
leaves2.value_counts()

#==============================================================================
# 3     33684: SGD SVM
# 6      2991: SGD SVM
# 10     1848: Naive Bayes/Logistic Regression
# 4       914: Naive Bayes/Logistic Regression
# 7       300: Logistic Regression
# 13       20: Naive Bayes
# 11       14: Naive Bayes

# 需要导入模块: from sklearn.tree import DecisionTreeClassifier [as 别名]
# 或者: from sklearn.tree.DecisionTreeClassifier import apply [as 别名]
@author: Samruddhi Somani
"""
execfile('Original.py')
execfile('tfidf.py')

from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import SGDClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.ensemble import RandomForestClassifier
import numpy as np

#fitting/examining tree
s2=DecisionTreeClassifier(max_depth=3, random_state=5)
s2.fit(x,cuisine)
leaves2=pd.Series(s2.apply(x),name='leaves')
idk=pd.concat([cuisine,leaves2],axis=1)
m=list(leaves2.value_counts().index.values) #[3, 6, 10, 4, 7, 13, 11, 14]
for y in m:
    print y
    print idk[leaves2==y]['cuisine'].value_counts()
leaves2.value_counts()

#==============================================================================
# 3     33684: SGD SVM
# 6      2991: SGD SVM
# 10     1848: Naive Bayes/Logistic Regression
# 4       914: Naive Bayes/Logistic Regression
# 7       300: Logistic Regression
# 13       20: Naive Bayes
# 11       14: Naive Bayes