本文整理汇总了Python中feature_extractor.FeatureExtractor.extract_full_feature_matrix方法的典型用法代码示例。如果您正苦于以下问题:Python FeatureExtractor.extract_full_feature_matrix方法的具体用法?Python FeatureExtractor.extract_full_feature_matrix怎么用?Python FeatureExtractor.extract_full_feature_matrix使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类feature_extractor.FeatureExtractor
的用法示例。
在下文中一共展示了FeatureExtractor.extract_full_feature_matrix方法的1个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from feature_extractor import FeatureExtractor [as 别名]
# 或者: from feature_extractor.FeatureExtractor import extract_full_feature_matrix [as 别名]
class RelationshipPostClassifier:
"""
Main class for classification and prediction
"""
def __init__(self, classifier_type="tree"):
self.data = None
self.classifier_type = classifier_type
self.classifier = None
self.featureExtractor = None
self.predictions = None
def read_csv_data(self, csv_file, maxrows=None):
"""
Read in data from given csv_file into self.data (pandas dataframe)
maxrows limits number of read rows.
:param csv_file:
:param maxrows:
:return: None
"""
sys.stderr.write("Reading in data from " + csv_file + "\n")
if maxrows:
self.data = pan.read_csv(csv_file, nrows=maxrows, encoding='utf-8')
else:
self.data = pan.read_csv(csv_file, encoding='utf-8')
def train_model(self, model_out_file):
"""
Extract the features from self.data and train the classifier. Output pickled model to model_out_file
:param model_out_file:
:return: None
"""
if self.data is None:
raise Exception("Trying to train model without any data.")
sys.stderr.write("Extracting features from data.\n")
self.featureExtractor = FeatureExtractor(self.data)
feature_matrix = self.featureExtractor.extract_full_feature_matrix()
labels = np.array([0 if lab == "Romantic" else 1 for lab in self.data["is_romantic"]])
sys.stderr.write("Training classifier.\n")
self.classifier = LogisticRegression() if self.classifier_type == "logit" else DecisionTreeClassifier()
self.classifier.fit(feature_matrix, labels)
sys.stderr.write("Saving classifier.\n")
with open(model_out_file, "w") as f:
pickle.dump(self.classifier, f)
def predict_model(self, model_file=None, output_file=None, output_probability_file=None):
"""
Predict classes on self.data and output to output_file
:param model_file: Model file to read model in from. Otherwise looks for self.classifier
:param output_file: File to save predictions in
:param output_probability_file: File to save predicted probabilities in
:return: predicted classes (array)
"""
if not self.classifier:
if not model_file:
raise Exception("No model to predict with.")
else:
with open(model_file) as f:
self.classifier = pickle.load(f)
if self.data is None:
raise Exception("Trying to predict using model with no data loaded.")
self.featureExtractor = FeatureExtractor(self.data)
feature_matrix = self.featureExtractor.extract_full_feature_matrix()
self.predictions = self.classifier.predict(feature_matrix)
if output_file is not None:
np.savetxt(output_file, self.predictions, delimiter=",", fmt="%d")
if output_probability_file is not None:
pred_probs = self.classifier.predict_proba(feature_matrix)
np.savetxt(output_probability_file, pred_probs, delimiter=",", fmt="%.3f")
return self.predictions