python scikit learn 模板

#!usr/bin/env python
# -*- coding: utf-8 -*-

import sys
import os
import time
from sklearn import metrics
import numpy as np
import cPickle as pickle

reload(sys)
sys.setdefaultencoding('utf8')

# Multinomial Naive Bayes Classifier
def naive_bayes_classifier(train_x, train_y):
from sklearn.naive_bayes import MultinomialNB
model = MultinomialNB(alpha=0.01)
model.fit(train_x, train_y)
return model

# KNN Classifier
def knn_classifier(train_x, train_y):
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier()
model.fit(train_x, train_y)
return model

# Logistic Regression Classifier
def logistic_regression_classifier(train_x, train_y):
from sklearn.linear_model import LogisticRegression
model = LogisticRegression(penalty='l2')
model.fit(train_x, train_y)
return model

# Random Forest Classifier
def random_forest_classifier(train_x, train_y):
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=8)
model.fit(train_x, train_y)
return model

# Decision Tree Classifier
def decision_tree_classifier(train_x, train_y):
from sklearn import tree
model = tree.DecisionTreeClassifier()
model.fit(train_x, train_y)
return model

# GBDT(Gradient Boosting Decision Tree) Classifier
def gradient_boosting_classifier(train_x, train_y):
from sklearn.ensemble import GradientBoostingClassifier
model = GradientBoostingClassifier(n_estimators=200)
model.fit(train_x, train_y)
return model

# SVM Classifier
def svm_classifier(train_x, train_y):
from sklearn.svm import SVC
model = SVC(kernel='rbf', probability=True)
model.fit(train_x, train_y)
return model

# SVM Classifier using cross validation
def svm_cross_validation(train_x, train_y):
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC
model = SVC(kernel='rbf', probability=True)
param_grid = {'C': [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], 'gamma': [0.001, 0.0001]}
grid_search = GridSearchCV(model, param_grid, n_jobs=1, verbose=1)
grid_search.fit(train_x, train_y)
best_parameters = grid_search.best_estimator_.get_params()
for para, val in best_parameters.items():
print para, val
model = SVC(kernel='rbf', C=best_parameters['C'], gamma=best_parameters['gamma'], probability=True)
model.fit(train_x, train_y)
return model

def read_data_mnist(data_file):
import gzip
f = gzip.open(data_file, "rb")
train, val, test = pickle.load(f)
f.close()
train_x = train[0]
train_y = train[1]
test_x = test[0]
test_y = test[1]
return train_x, train_y, test_x, test_y

def read_data_conversation(data_file):
data_x = []
data_y = []
with open(data_file) as f:
for line in f:
strArray = line.split(" ")
floatArray = [float(x) for x in strArray]
data_x.append(floatArray[1:])
data_y.append(floatArray[0])
return np.array(data_x), np.array(data_y)

def read_data(train_file, test_file):
train_x, train_y = read_data_conversation(train_file)
test_x, test_y = read_data_conversation(test_file)
return train_x, train_y, test_x, test_y

def evaluate(is_binary_class, predict, predict_pos, test_y):
if is_binary_class:
precision = metrics.precision_score(test_y, predict)
recall = metrics.recall_score(test_y, predict)
print 'precision: %.3f%%\nrecall: %.3f%%' % (100 * precision, 100 * recall)
accuracy = metrics.accuracy_score(test_y, predict)
print 'accuracy: %.3f%%' % (100 * accuracy)
roc_auc = metrics.roc_auc_score(test_y, predict_pos)
print 'roc_auc: %.3f' % roc_auc

if __name__ == '__main__':
data_file = "mnist.pkl.gz"
thresh = 0.9
model_save_file = None
model_save = {}

test_classifiers = ['NB',
# 'KNN',
'LR',
'RF',
'DT',
'SVM',
'GBDT'
]
classifiers = {'NB': naive_bayes_classifier,
'KNN': knn_classifier,
'LR': logistic_regression_classifier,
'RF': random_forest_classifier,
'DT': decision_tree_classifier,
'SVM': svm_classifier,
'SVMCV': svm_cross_validation,
'GBDT': gradient_boosting_classifier
}

print 'reading training and testing data...'
train_x, train_y, test_x, test_y = read_data("QAFormatResult-train-format.txt", "QAFormatResult-test-format.txt")
num_train, num_feat = train_x.shape
num_test, num_feat = test_x.shape
is_binary_class = (len(np.unique(train_y)) == 2)
print '******************** Data Info *********************'
print '#training data: %d, #testing_data: %d, dimension: %d' % (num_train, num_test, num_feat)
print 'testing train data... '
print train_x[0]
print train_y[0]
print 'testing test data... '
print test_x[0]
print test_y[0]

ensemble_train_x = None
ensemble_test_x = None
voting_predict = None

for classifier in test_classifiers:
print '******************* %s ********************' % classifier
start_time = time.time()
model = classifiers[classifier](train_x, train_y)
print 'training took %fs!' % (time.time() - start_time)

predict_proba = model.predict_proba(test_x)
predict_pos = predict_proba[:, 1]
predict = np.array([int(x + 0.5) for x in predict_pos.tolist()])
# print predict
# predict = model.predict(test_x)

if voting_predict is None:
voting_predict = predict
else:
voting_predict = np.vstack((voting_predict, predict))

if ensemble_test_x is None:
ensemble_test_x = predict_pos
else:
ensemble_test_x = np.vstack((ensemble_test_x, predict_pos))
train_pos = model.predict_proba(train_x)[:, 1]
if ensemble_train_x is None:
ensemble_train_x = train_pos
else:
ensemble_train_x = np.vstack((ensemble_train_x, train_pos))
if model_save_file != None:
model_save[classifier] = model
evaluate(is_binary_class, predict, predict_pos, test_y)

ensemble_train_x = ensemble_train_x.T
ensemble_test_x = ensemble_test_x.T
print '******************* ensemble ********************'
start_time = time.time()
model = logistic_regression_classifier(ensemble_train_x, train_y)
print 'training took %fs!' % (time.time() - start_time)
predict_proba = model.predict_proba(ensemble_test_x)
predict_pos = predict_proba[:, 1]
predict = np.array([int(x + 0.5) for x in predict_pos.tolist()])
# print predict
evaluate(is_binary_class, predict, predict_pos, test_y)

voting_predict = voting_predict.T
print '******************* voting ********************'
voting_predict = np.sum(voting_predict, axis=1)
predict = np.array([int(2 * (x - 0.1) / len(test_classifiers)) for x in voting_predict.tolist()])
# print predict
evaluate(is_binary_class, predict, predict, test_y)

if model_save_file != None:
pickle.dump(model_save, open(model_save_file, 'wb'))