Python基于sklearn库的分类算法简单应用示例

本文实例讲述了Python基于sklearn库的分类算法简单应用。分享给大家供大家参考，具体如下：

scikit-learn已经包含在Anaconda中。也可以在官方下载源码包进行安装。本文代码里封装了如下机器学习算法，我们修改数据加载函数，即可一键测试：

# coding=gbk
'''
Created on 2016年6月4日
@author: bryan
'''
import time
from sklearn import metrics
import pickle as pickle
import pandas as pd
# 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 list(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(data_file):
  data = pd.read_csv(data_file)
  train = data[:int(len(data)*0.9)]
  test = data[int(len(data)*0.9):]
  train_y = train.label
  train_x = train.drop('label', axis=1)
  test_y = test.label
  test_x = test.drop('label', axis=1)
  return train_x, train_y, test_x, test_y
if __name__ == '__main__':
  data_file = "H:\\Research\\data\\trainCG.csv"
  thresh = 0.5
  model_save_file = None
  model_save = {}
  test_classifiers = ['NB', 'KNN', 'LR', 'RF', 'DT', 'SVM','SVMCV', '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(data_file)
  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 = model.predict(test_x)
    if model_save_file != None:
      model_save[classifier] = model
    precision = metrics.precision_score(test_y, predict)
    recall = metrics.recall_score(test_y, predict)
    print('precision: %.2f%%, recall: %.2f%%' % (100 * precision, 100 * recall))
    accuracy = metrics.accuracy_score(test_y, predict)
    print('accuracy: %.2f%%' % (100 * accuracy))
  if model_save_file != None:
    pickle.dump(model_save, open(model_save_file, 'wb'))

测试结果如下：

reading training and testing data...
******************* NB ********************
training took 0.004986s!
precision: 78.08%, recall: 71.25%
accuracy: 74.17%
******************* KNN ********************
training took 0.017545s!
precision: 97.56%, recall: 100.00%
accuracy: 98.68%
******************* LR ********************
training took 0.061161s!
precision: 89.16%, recall: 92.50%
accuracy: 90.07%
******************* RF ********************
training took 0.040111s!
precision: 96.39%, recall: 100.00%
accuracy: 98.01%
******************* DT ********************
training took 0.004513s!
precision: 96.20%, recall: 95.00%
accuracy: 95.36%
******************* SVM ********************
training took 0.242145s!
precision: 97.53%, recall: 98.75%
accuracy: 98.01%
******************* SVMCV ********************
Fitting 3 folds for each of 14 candidates, totalling 42 fits
[Parallel(n_jobs=1)]: Done  42 out of  42 | elapsed:    6.8s finished
probability True
verbose False
coef0 0.0
degree 3
tol 0.001
shrinking True
cache_size 200
gamma 0.001
max_iter -1
C 1000
decision_function_shape None
random_state None
class_weight None
kernel rbf
training took 7.434668s!
precision: 98.75%, recall: 98.75%
accuracy: 98.68%
******************* GBDT ********************
training took 0.521916s!
precision: 97.56%, recall: 100.00%
accuracy: 98.68%

希望本文所述对大家Python程序设计有所帮助。