def compute_cross_correlation_score(df, clfs, preprocess_scaling=True, nFold=10):
"""
return an iterator with cross validation data
:param df:
:param clfs:
:param preprocess_scaling:
:param nFold:
:return:
"""
to_sklearn_features = DataFrameMapper([('features', sklearn.feature_extraction.DictVectorizer())])
data_X = to_sklearn_features.fit_transform(df)
data_Y = df.expected_class
skf = cross_validation.StratifiedKFold(data_Y, n_folds=nFold)
classification_results = []
scores = []
for num, (train_index, test_index) in enumerate(skf):
X_train, X_test = data_X[train_index], data_X[test_index]
Y_train, Y_test = data_Y[train_index], data_Y[test_index]
print("Len train{}, Len test{}".format(Y_train.size, Y_test.size))
cross_valid_data = Cross_validation_split(X_train, X_test, Y_train, Y_test)
cross_valid_data = preprocess(cross_valid_data, preprocess_scaling=preprocess_scaling, preprocess_correlation=False)
for clf in clfs:
score, classification = generate_score(clf, cross_valid_data, fold=num)
scores.append(score)
classification_results.append(classification)
return scores, classification_results
def generate_res_as_in_paper(df, list_of_classifiers, preprocess_scaling=True, preprocess_correlation=False):
res = []
for fold in set(df.fold):
cross_valid_data = compute_cross_validation_fold(df, fold)
cross_valid_data = preprocess(cross_valid_data, preprocess_scaling=preprocess_scaling, preprocess_correlation=preprocess_correlation)
for clf in list_of_classifiers:
res.append(generate_score(clf, cross_valid_data)[0])
return res
def generate_res_as_in_paper(df,
list_of_classifiers,
preprocess_scaling=True,
preprocess_correlation=False):
res = []
for fold in set(df.fold):
cross_valid_data = compute_cross_validation_fold(df, fold)
cross_valid_data = preprocess(
cross_valid_data,
preprocess_scaling=preprocess_scaling,
preprocess_correlation=preprocess_correlation)
for clf in list_of_classifiers:
res.append(generate_score(clf, cross_valid_data)[0])
return res
def compute_cross_correlation_score(df,
clfs,
preprocess_scaling=True,
nFold=10):
"""
return an iterator with cross validation data
:param df:
:param clfs:
:param preprocess_scaling:
:param nFold:
:return:
"""
to_sklearn_features = DataFrameMapper([
('features', sklearn.feature_extraction.DictVectorizer())
])
data_X = to_sklearn_features.fit_transform(df)
data_Y = df.expected_class
skf = cross_validation.StratifiedKFold(data_Y, n_folds=nFold)
classification_results = []
scores = []
for num, (train_index, test_index) in enumerate(skf):
X_train, X_test = data_X[train_index], data_X[test_index]
Y_train, Y_test = data_Y[train_index], data_Y[test_index]
print("Len train{}, Len test{}".format(Y_train.size, Y_test.size))
cross_valid_data = Cross_validation_split(X_train, X_test, Y_train,
Y_test)
cross_valid_data = preprocess(cross_valid_data,
preprocess_scaling=preprocess_scaling,
preprocess_correlation=False)
for clf in clfs:
score, classification = generate_score(clf,
cross_valid_data,
fold=num)
scores.append(score)
classification_results.append(classification)
return scores, classification_results