def predict(clf, f_predict_vect, f_predict_id_set, f_predict_out):
"""
根据预测数据，给出预测结果
Args:
clf: 分类器
f_predict_vect: fin, 预测数
f_predict_id_set: fin, 与预测数据对应的存放有user_id, item_id的文件
f_predict_out: fout, 存放预测结果的文件
Returns:
f_predict_out: fout, 存放预测结果的文件
"""
predict_X, predict_y = generate_X_y_arrays(f_predict_vect)
logger.debug('predict start.')
predict_y = clf.predict(predict_X)
logger.debug('predict done, predict result size=%s' % (len(predict_y)))
with open(f_predict_id_set, 'r') as fin, open(f_predict_out, 'w') as fout:
counter = 0
fin.readline() # 忽略首行
fout.write('user_id,item_id,tag')
logger.debug('start store predict result')
for line in fin:
line_result = line.strip() + ',%s\n' % (predict_y[counter])
fout.write(line_result)
counter += 1
if counter != len(predict_y):
assert(counter == len(predict_y))
logger.error('predict result size:%s, but uid_iid_set size:%s' % (len(predict_y), counter))
else:
logger.info('predict success, generate predict result in %s' % (f_predict_out))
return f_predict_out
def train(clf, f_train_set):
"""
训练分类器
Args:
clf: 分类器
f_train_set: fin, 训练集文件
Returns:
clf: 分类器
"""
from sklearn import cross_validation
(X, y) = generate_X_y_arrays(f_train_set)
# 简单验证
#logger.debug('Start simple cross-validate.')
#scores = cross_validation.cross_val_score(clf, X, y, cv=5)
#logger.info('Classifier simple cross-validated(use train set) scores ars %s' % (scores))
# 训练
clf.fit(X, y)
logger.info('Classifier(%s) fit Done.' % (clf))
#logger.info('LR classifier(%s) fit Done. And Coef are: %s' % (clf, clf.coef_))
#logger.info('SVM classifier(%s) fit Done. Best params are %s with a best score of %0.2f' % (clf, clf.best_params_, clf.best_score_))
return clf
def generate_predict_result(f_predict='%s/predict_set/predict_result.csv' % (data_path),
f_vec_set='%s/predict_set/predict_combined_vec_data.csv' % (data_path),
f_uid_iid_set='%s/predict_set/predict_set.csv' % (data_path)):
"""
生成预测结果
Args:
f_predict: string, 存放预测结果
f_vec_set: string, 存放待预测向量的文件名
f_uid_iid_set: string, 存放与向量对应的user_id, item_id
Returns:
"""
predict_X, predict_y = generate_X_y_arrays(f_vec_set)
logger.debug('predict start.')
predict_y = clf.predict(predict_X)
logger.debug('predict done, predict result size=%s' % (len(predict_y)))
with open(f_uid_iid_set, 'r') as fin, open(f_predict, 'w') as fout:
counter = 0
fin.readline() # 忽略首行
fout.write('user_id,item_id,tag')
logger.debug('start store predict result')
for line in fin:
line_result = line.strip() + ',%s\n' % (predict_y[counter])
fout.write(line_result)
counter += 1
if counter != len(predict_y):
logger.error('predict result size:%s, but uid_iid_set size:%s' % (len(predict_y), counter))
else:
logger.info('predict success, generate predict result in %s' % (f_predict))
def train(clf, f_train_set):
"""
训练分类器
Args:
clf: 分类器
f_train_set: fin, 训练集文件
Returns:
clf: 分类器
"""
from sklearn import cross_validation
(X, y) = generate_X_y_arrays(f_train_set)
# 简单验证
#logger.debug('Start simple cross-validate.')
#scores = cross_validation.cross_val_score(clf, X, y, cv=5)
#logger.info('Classifier simple cross-validated(use train set) scores ars %s' % (scores))
# 训练
clf.fit(X, y)
logger.info('Classifier(%s) fit Done.' % (clf))
#logger.info('LR classifier(%s) fit Done. And Coef are: %s' % (clf, clf.coef_))
#logger.info('SVM classifier(%s) fit Done. Best params are %s with a best score of %0.2f' % (clf, clf.best_params_, clf.best_score_))
return clf
def train_svm():
"""
训练分类器
Args:
None
Returns:
None
"""
(X, y) = generate_X_y_arrays('%s/train_combined_vec_data.csv' % (data_path))
clf.fit(X, y)
logger.info('Classifier fit Done. Best params are %s with a best score of %0.2f' % (clf.best_params_, clf.best_score_))
def train_svm():
"""
训练分类器
Args:
None
Returns:
None
"""
(X,
y) = generate_X_y_arrays('%s/train_combined_vec_data.csv' % (data_path))
clf.fit(X, y)
logger.info(
'Classifier fit Done. Best params are %s with a best score of %0.2f' %
(clf.best_params_, clf.best_score_))
def train_svm(clf,
f_train_set='%s/train_combined_vec_data.csv' % (data_path)):
"""
训练SVM分类器
Args:
clf: 分类器
f_train_set: string, 训练集文件
Returns:
clf: 分类器
"""
from sklearn import cross_validation
(X, y) = generate_X_y_arrays(f_train_set)
# 简单验证
scores = cross_validation.cross_val_score(clf, X, y, cv=5)
logger.info('SVM classifier simple cross-validated scores ars %s' % (scores))
# 训练
clf.fit(X, y)
logger.info('SVM classifier(%s) fit Done. Best params are %s with a best score of %0.2f' % (clf, clf.best_params_, clf.best_score_))
return clf
def train_clf(clf,
f_train_set='%s/train_combined_vec_data.csv' % (data_path)):
"""
训练分类器
Args:
clf: 分类器
f_train_set: string, 训练集文件
Returns:
clf: 分类器
"""
from sklearn import cross_validation
(X, y) = generate_X_y_arrays(f_train_set)
# 简单验证
scores = cross_validation.cross_val_score(clf, X, y, cv=5)
logger.info('Classifier simple cross-validated scores ars %s' % (scores))
# 训练
clf.fit(X, y)
logger.info('Classifier(%s) fit Done.' % (clf))
return clf
def predict(clf, f_predict_vect, f_predict_id_set, f_predict_out):
"""
根据预测数据，给出预测结果
Args:
clf: 分类器
f_predict_vect: fin, 预测数
f_predict_id_set: fin, 与预测数据对应的存放有user_id, item_id的文件
f_predict_out: fout, 存放预测结果的文件
Returns:
f_predict_out: fout, 存放预测结果的文件
"""
predict_X, predict_y = generate_X_y_arrays(f_predict_vect)
logger.debug('predict start.')
predict_y = clf.predict(predict_X)
logger.debug('predict done, predict result size=%s' % (len(predict_y)))
with open(f_predict_id_set, 'r') as fin, open(f_predict_out, 'w') as fout:
counter = 0
fin.readline() # 忽略首行
fout.write('user_id,item_id,tag')
logger.debug('start store predict result')
for line in fin:
line_result = line.strip() + ',%s\n' % (predict_y[counter])
fout.write(line_result)
counter += 1
if counter != len(predict_y):
assert (counter == len(predict_y))
logger.error('predict result size:%s, but uid_iid_set size:%s' %
(len(predict_y), counter))
else:
logger.info('predict success, generate predict result in %s' %
(f_predict_out))
return f_predict_out
def generate_predict_result(
f_predict='%s/predict_set/predict_result.csv' % (data_path),
f_vec_set='%s/predict_set/predict_combined_vec_data.csv' % (data_path),
f_uid_iid_set='%s/predict_set/predict_set.csv' % (data_path)):
"""
生成预测结果
Args:
f_predict: string, 存放预测结果
f_vec_set: string, 存放待预测向量的文件名
f_uid_iid_set: string, 存放与向量对应的user_id, item_id
Returns:
"""
predict_X, predict_y = generate_X_y_arrays(f_vec_set)
logger.debug('predict start.')
predict_y = clf.predict(predict_X)
logger.debug('predict done, predict result size=%s' % (len(predict_y)))
with open(f_uid_iid_set, 'r') as fin, open(f_predict, 'w') as fout:
counter = 0
fin.readline() # 忽略首行
fout.write('user_id,item_id,tag')
logger.debug('start store predict result')
for line in fin:
line_result = line.strip() + ',%s\n' % (predict_y[counter])
fout.write(line_result)
counter += 1
if counter != len(predict_y):
logger.error('predict result size:%s, but uid_iid_set size:%s' %
(len(predict_y), counter))
else:
logger.info('predict success, generate predict result in %s' %
(f_predict))
