def rank_features_rfe(X, y, featureset):
"""Rank features by their importance using recursive feature elimination.
:param X: A training set of features.
:param y: A target set (aka class labels for the training set)
:param featureset: An instance of a featureset (such as Basic9Extractor())
:rtype: An OrderedDict of the form {K : V}, with K being the feature name
and V being its importance. This dictionary will be sorted by importance.
"""
# FIXME: Use an RBF SVC to rank features. It is likely that the "importance"
# rankings derived from a LinearSVC are similar as an RBF kernel SVM, but,
# for safety's sake, it is best to assume they are not.
classifier = LinearSVC()
classifier.fit(X, y)
ranker = RFE(classifier, 1, step=1)
ranker = ranker.fit(X, y)
# Get the names of the feature columns.
# FIXME: Duplicate code from rank_features. Make this its own function.
feat_importance = OrderedDict()
for index, func in enumerate(featureset.features):
feat_importance[func] = ranker.ranking_[index]
return sorted(feat_importance.items(), key=lambda x: x[1])
def select_features(X, y, random_state, kernel='linear', C=1.0, num_attributes=3):
"""
Uses Support Vector Classifier as the estimator to rank features
with Recursive Feature Eliminatin.
Parameters
----------
X: A pandas.DataFrame. Attributes.
y: A pandas.DataFrame. Labels.
random_state: A RandomState instance. Used in SVC().
kernel: A string. Used in SVC(). Default: "linear".
C: A float. Used in SVC(). Default: 1.0.
num_attributes: An int. The number of features to select in RFE. Default: 3.
Returns
-------
A 3-tuple of (RFE, np.ndarray, np.ndarray)
model: An RFE instance.
columns: Selected features.
ranking: The feature ranking. Selected features are assigned rank 1.
"""
rfe = RFE(svm.SVC(C, kernel, random_state=random_state), num_attributes)
model = rfe.fit(X, y.values.ravel())
columns = list()
for idx, label in enumerate(X):
if rfe.support_[idx]:
columns.append(label)
ranking = rfe.ranking_
return model, columns, ranking
def get_best_cols(df):
""" select best cols with RFE """
# factors
cols_to_factor = [
pd.get_dummies(df.X7),
pd.get_dummies(df.X8),
pd.get_dummies(df.X9),
pd.get_dummies(df.X11),
pd.get_dummies(df.X12),
pd.get_dummies(df.X14),
pd.get_dummies(df.X12),
pd.get_dummies(df.X14),
pd.get_dummies(df.X32),
]
# dataframe with factors blown out
df_f = pd.concat(cols_to_factor, axis=1)
# numerics
RFE_col_list = ["X4", "X5", "X6", "X13", "X21", "X22", "X29", "X30", "X31"]
# dataframe with numerics
df_n = df.ix[:, RFE_col_list]
X = np.asarray(df_n)
X = StandardScaler().fit_transform(X)
# add in factors
X = np.concatenate([X, np.asarray(df_f)], axis=1)
# leave y alone
y = df.X1
# I don't like to guess yes this is only linear relationships
estimator = SVR(kernel="linear")
selector = RFE(estimator, 40, step=2)
selector = selector.fit(X, y)
# make index for merged df, yes this whines
df_index = df_n.columns + df_f.columns
best_cols = df_index[selector.support_]
return best_cols
def recursive_feature_elimination(config_learning, config_data, number_features):
output = open(os.path.expanduser(config_data.get("Learner", "models")) + "/" + "feature_ranks.txt", "w")
feature_names = FeatureExtractor.get_combinations_from_config_file_unsorted(config_data)
x_train = read_features_file(config_learning.get('x_train'), '\t')
y_train = read_reference_file(config_learning.get('y_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
estimator, scorers = learn_model.set_learning_method(config_learning, x_train, y_train)
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
rfe = RFE(estimator, number_features, step=1)
rfe.fit(x_train, y_train)
for i, name in enumerate(feature_names):
output.write(name + "\t" + str(rfe.ranking_[i]) + "\n")
print(name + "\t" + str(rfe.ranking_[i]))
predictions = rfe.predict(x_test)
output.close()
return predictions
def test_deeply_nested():
# Render a deeply nested estimator
rfe = RFE(RFE(RFE(RFE(RFE(RFE(RFE(LogisticRegression())))))))
expected = """
RFE(estimator=RFE(estimator=RFE(estimator=RFE(estimator=RFE(estimator=RFE(estimator=RFE(estimator=LogisticRegression(C=1.0,
class_weight=None,
dual=False,
fit_intercept=True,
intercept_scaling=1,
l1_ratio=None,
max_iter=100,
multi_class='warn',
n_jobs=None,
penalty='l2',
random_state=None,
solver='warn',
tol=0.0001,
verbose=0,
warm_start=False),
n_features_to_select=None,
step=1,
verbose=0),
n_features_to_select=None,
step=1,
verbose=0),
n_features_to_select=None,
step=1, verbose=0),
n_features_to_select=None, step=1,
verbose=0),
n_features_to_select=None, step=1, verbose=0),
n_features_to_select=None, step=1, verbose=0),
n_features_to_select=None, step=1, verbose=0)"""
expected = expected[1:] # remove first \n
assert rfe.__repr__() == expected
def recursiveFeatureSelector(classifier_model,train_data,train_labels,test_data,number_of_features):
rfe = RFE(classifier_model,number_of_features)
transformed_train_data = rfe.fit_transform(train_data,train_labels)
transformed_test_data = rfe.transform(test_data)
return transformed_train_data,transformed_test_data
def doRFE(self, X, y):
# do RFE
self.numFeatures = X.shape[1]
svc = SVC(kernel="linear", C=self.C)
rfe = RFE(estimator=svc, n_features_to_select=1, step=1)
rfe.fit(X, y)
self.feature_importances_ = self._getImportances(rfe.ranking_)
def feature_sorting(features_values_temp, rows_temp, columns_temp, prediction_values_temp, kernel, threshold): rows = 0 while rows_temp > 0: rows = rows + 1 rows_temp = rows_temp - 1 columns = 0 while columns_temp > 0: columns = columns + 1 columns_temp = columns_temp - 1 features_values = [x for x in features_values_temp] prediction_values = [y for y in prediction_values_temp] rotated = convert_list_to_matrix(features_values, rows, columns) # print rotated.shape scores = np.array(prediction_values) threshold = float(threshold) estimator = SVR(kernel=kernel) # try to change to the model for which the test is gonna run (lasso, ridge, etc.) selector = RFE(estimator, 0, step=1) selector = selector.fit(rotated, scores) features_used = [i for i, x in enumerate(selector.support_) if x == True] # i+1 b/c matlab starts indexing from 1 return selector.ranking_.tolist()
def test_main():
iris = load_iris()
x, y = iris.data, iris.target
estimator = SVR(kernel="linear")
selector = RFE(estimator, 2 , step=1)
selector = selector.fit(x, y)
print selector.support_
def ref(X, y, n_features_to_select=1, kernel='linear'):
# specify the desired number of features
# return the masks and ranking of selected features
estimator = SVC(kernel=kernel, class_weight='balanced')
selector = RFE(estimator, n_features_to_select=n_features_to_select, step=1)
selector = selector.fit(X, y)
return (selector)
def recursiveFeatureSelection():
X = np.array(trainingData, dtype=float)
y = np.array(trainingDataLabels, dtype=float)
svc = SVC("linear", 1)
rfe = RFE(svc, 1, 1)
rfe.fit(X, y)
print rfe
def featSelect(label,trainSet,trainObs,cv,numFeat=5,SEED=34,name=''):
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from numpy import zeros
model = LogisticRegression(random_state=SEED)
predCv = zeros(len(trainObs))
rfe = RFE(model, numFeat, step=1)
rfe.fit(trainSet,trainObs)
vars = list(trainSet.columns[rfe.ranking_ == 1])
auc = 0
for i in range(1,max(rfe.ranking_)):
for tr, vl in cv:
model.fit(trainSet[vars + list(trainSet.columns[rfe.ranking_ == i])].ix[tr],trainObs[tr])
predCv[vl] = model.predict_proba(trainSet[vars + list(trainSet.columns[rfe.ranking_ == i])].ix[vl])[:,1]
if roc_auc_score(trainObs,predCv) > auc:
auc = roc_auc_score(trainObs,predCv)
vars += list(trainSet.columns[rfe.ranking_ == i])
for v in vars:
for tr, vl in cv:
model.fit(trainSet[[x for x in vars if x != v]].ix[tr],trainObs[tr])
predCv[vl] = model.predict_proba(trainSet[[x for x in vars if x != v]].ix[vl])[:,1]
if roc_auc_score(trainObs,predCv) > auc:
auc = roc_auc_score(trainObs,predCv)
vars.remove(v)
for v in [x for x in trainSet.columns if x not in vars]:
for tr, vl in cv:
model.fit(trainSet[vars + [v]].ix[tr],trainObs[tr])
predCv[vl] = model.predict_proba(trainSet[vars + [v]].ix[vl])[:,1]
if roc_auc_score(trainObs,predCv) > auc:
auc = roc_auc_score(trainObs,predCv)
vars += [v]
print name,"Final AUC: ",auc
return {label: vars}
def get_model_RFE_top_features(self,expression_file,ic50_file,target_features,drug):
expression_frame,ic50_series = dfm.get_expression_frame_and_ic50_series_for_drug(expression_file, ic50_file,drug,normalized=True,trimmed=True,threshold=None)
scikit_data,scikit_target = dfm.get_scikit_data_and_target(expression_frame,ic50_series)
step_length = int(len(scikit_data.tolist()[0]) / 100) + 1
selector = RFE(self.model,int(target_features),step=step_length)
selector.fit(scikit_data,scikit_target)
return [expression_frame.index[i] for i in xrange(0,len(expression_frame.index)) if selector.support_[i]]
def LogReg(X_train, X_test, y_train, y_test, Min_N_Feat, Max_N_Feat, mask='None',weights='auto'):
#******************************************************************************
from sklearn.feature_selection import RFE #import the library to rank features with recursive feature elimination
from sklearn.linear_model import LogisticRegression as LogR #import the Logistic Regression module
if mask=='None':
mask = np.zeros((Max_N_Feat-Min_N_Feat+1,int(X_train.shape[1])),dtype='bool') #define the mask to obtain the list of selected features
#end
Pred_Train = np.zeros((int(max(y_train.shape)),Max_N_Feat-Min_N_Feat+1),dtype='int') #define the matrix of outputs (each prediction set is stored in a different column)
Pred_Test = np.zeros((int(max(y_test.shape)),Max_N_Feat-Min_N_Feat+1),dtype='int') #define the matrix of outputs (each prediction set is stored in a different column)
print 'Logistic Regression: Training...' #notify the user about the status of the process
for ift in range(Min_N_Feat,Max_N_Feat+1): #iterate across the maximum number of features
LogReg_obj = LogR(C=1e3, class_weight=weights) #create the logistic regression model
if mask=='None':
rfe = RFE(LogReg_obj, ift) #create the RFE model and select the number of attributes
rfe = rfe.fit(X_train,y_train) #train the RFE (feature selection) model on the train data sets
mask[ift-Min_N_Feat,:] = rfe.support_ #apply the best feature mask to the output mask
#end
LogReg_obj.fit(X_train[:,mask[ift-Min_N_Feat,:]], y_train) #fit the logistic model to the train data sets
Pred_Train[:,ift-1] = LogReg_obj.predict(X_train[:,mask[ift-Min_N_Feat,:]]) #apply the logistic model to the train dataset
Pred_Test[:,ift-1] = LogReg_obj.predict(X_test[:,mask[ift-Min_N_Feat,:]]) #apply the logistic model to the test dataset
print 'Logistic Regression: Predicting...', 100*ift/(Max_N_Feat-Min_N_Feat+1), '%' #notify the user about the status of the process
#end
print 'Logistic Regression: Completed!' #notify the user about the status of the process
return Pred_Train, Pred_Test, mask
def remove_one_feature(X, Y, names): lr = LinearRegression() rfe = RFE(lr, n_features_to_select=1) rfe.fit(X,Y) rank = (sorted(zip(map(lambda x: round(x, 4), rfe.ranking_), names))) print(rank) return rank[-1][1]
def selectFeaturesFromSubsetRecursive(self,subset,numFeatures): model = svm.LinearSVC(class_weights='auto') rfe = RFE(model, numFeatures) rfe = rfe.fit(self.instances[:,subset], self.classes) # summarize the selection of the attributes # print(rfe.get_support(indices=True)) # print(rfe.ranking_) return rfe.get_support(indices=True)
def buildTree(self,depth):
#Here, we define the parameters of our tree and use a feature selection algorithm (RFE) to pick out the strongest features.
self.tree = DecisionTreeClassifier(criterion = 'entropy', max_depth=depth, random_state=0)
selector = RFE(self.tree, 2, step=1)
selector = selector.fit(self.X_train, self.Y_train)
selector.support_
selector.ranking_
def rec_feature_elim(data,num_features=17700):
X = data.get_gene_exp_matrix()
y = data.get_labels()
svc = SVC(kernel="linear", C=1)
rfe = RFE(estimator=svc, n_features_to_select=num_features, step=1)
selector = rfe.fit(X, y)
mask = map(lambda x: 1 if x is True else 0,selector.support_)
print_genes_nonzero_coeff(data,mask)
def build_model(x,y,no_features):
"""
Build a linear regression model
"""
model = LinearRegression(normalize=True,fit_intercept=True)
rfe_model = RFE(estimator=model,n_features_to_select=no_features)
rfe_model.fit(x,y)
return rfe_model
def recursive_feature_elimination(X, y):
model = LogisticRegression()
# create the RFE model and select 3 attributes
rfe = RFE(model, 3)
rfe = rfe.fit(X, y)
# summarize the selection of the attributes
print(rfe.support_)
print(rfe.ranking_)
def feature_selection(X, y):
model = LR()
rfe = RFE(model, 10)
fit = rfe.fit(X, y)
print("Num Features: %d") % fit.n_features_
print("Selected Features: %s") % fit.support_
print("Feature Ranking: %s") % fit.ranking_
print fit.score(X, y)
return fit.transform(X)
def quick_rfe(estimator, X, y):
rfe = RFE(estimator = estimator, n_features_to_select = 1)
rfe.fit(X,y)
features = X.columns.tolist()
sorted_features = [f for (rank, f) in sorted(zip(rfe.ranking_, features))]
return sorted_features, rfe.ranking_
class LogReg:
"""
Initialization sets the objects model, vectorizer, labels, and corpus
variables. Initialization also performs the initial training for the model
and vectorizer using the given reviews.
"""
def __init__(
self,
reviews,
vectorizer = TfidfVectorizer(stop_words = 'english', max_df = 1,
ngram_range = (1, 2)),
model = LogisticRegression()
):
self.model = model
self.vectorizer = vectorizer
self.selector = RFE(self.model, step = 100, verbose = 100)
corpus = []
labels = []
for review in reviews:
corpus += [review[1]["text"]]
labels += [review[0]]
#setting variables for the object
self.corpus = corpus
self.labels = labels
self.reviews = reviews
X = self.vectorizer.fit_transform(self.corpus)
self.feature_names = self.vectorizer.get_feature_names()
y = self.labels
for string in self.feature_names:
print(string.encode("ascii", 'ignore'))
#Training the model
X_new = self.selector.fit_transform(X, self.labels)
self.model.fit(X_new, self.labels)
def classify_all(self, all_test_data):
test_corpus = []
y = []
for review in all_test_data:
test_corpus += [review[1]['text']]
y += [review[0]]
#Used transform instead of fit_transform
#for test data so number of features will match
X = self.vectorizer.transform(test_corpus)
X_new = self.selector.transform(X)
results = self.model.predict(X_new)
categories = ["spring", "summer", "fall", "winter"]
for i, category in enumerate(categories):
top10 = np.argsort(self.model.coef_[i])[-20:]
for j in top10:
print("%s: %s" % (category, "".join(self.feature_names[j])))
return results
def recurrciveFE(self, data):
"""
Uses Recurrcise Feature Elimination to determine the write number of
features before adding additional leads to overfitting &
It works by recursively removing attributes and building a model on those
attributes that remain. It uses the model accuracy to identify
which attributes (and combination of attributes) contribute the
most to predicting the target attribute.
Parameters
----------
data : DataFrame
Input data, for which categorical variables should be converted
response should be in 0 column, predictors in additional
Returns
-------
out : Plot
A plot with the number of optimal number of features,
which is then used to determine features of most
importance returned in a print out to console
"""
features_list = data.columns.values[1::]
predictors = np.asarray(data.values[:, 1::])
response = np.asarray(data.values[:, 0])
estimator = SVC(kernel="linear")
###using cross validation to determine nooffeatures
rfecv = RFE(estimator, step=1, cv=StratifiedKFold(response, 2), scoring = 'accuracy')
rfecv.fit(predictors, response)
RFE( )
print("Optimal number of features : %d" % rfecv.n_features_)
# Plot number of features VS. cross-validation scores
plt.figure()
plt.xlabel("Number of features selected")
plt.ylabel("Cross validation score (nb of correct classifications)")
plt.plot(range(1, len(rfecv.grid_scores_) + 1), rfecv.grid_scores_)
plt.show()
##label as optimal #of features
noffeatures = rfecv.n_features_
##use rfe to determine top features
selector = RFE(estimator,noffeatures , step=1)
selector = selector.fit(predictors, response)
##creat index to get names
index1 = np.where(selector.support_ == False)[0]
index = np.argsort(selector.ranking_[index1])[::-1]
feature_list_imp = features_list[index]
for f in range(index.shape[0]):
print("%d. feature %d (%s)" % (f + 1, index[f], feature_list_imp[index[f]]))
print(selector.support_)
print(selector.ranking_)
def recursive_fs(X, y, clf, num_features):
# create the RFE model and select 3 attributes
rfe = RFE(clf, num_features)
start = time.time()
rfe = rfe.fit(X, y)
# summarize the selection of the attributes
end = time.time()
print ("Training Time: " + str((end - start)) + "s")
return rfe
def feature_selection(estimator, x, y):
"""
支持度评级
"""
selector = RFE(estimator)
selector.fit(x, y)
print('RFE selection')
print(pd.DataFrame(
{'support': selector.support_, 'ranking': selector.ranking_},
index=pig_three_feature.columns[1:]))
def trainDesicionTreeClassifier():
modelDesicionTree=DecisionTreeClassifier(max_depth=5)
# set the number of features to 10
rfedecisiontree = RFE(modelDesicionTree, 10)
rfedecisiontree = rfedecisiontree.fit(X_train, y_train)
print("Feature Importance of Decision Tree Model")
print(rfedecisiontree.support_)
print(rfedecisiontree.ranking_)
modelDesicionTree.fit(X_train, y_train)
return modelDesicionTree
def rank(training_set, paradigm_lengths, category_description):
transfomer = DataTransformer(training_set, paradigm_lengths, category_description)
headlines, matrix, targets = transfomer.get_training_data_matrix(normalize=True)
matrix = matrix.toarray()
estimator = svm.SVC(C=1, kernel='linear')
selector = RFE(estimator, 1, step=1)
selector = selector.fit(matrix, targets)
for i in range(len(headlines)):
print headlines[i], selector.ranking_[i]
def trainLogisticRegression():
modelLogisticRegression=LogisticRegression()
#set the number of features to 10
rfelogisticReg=RFE(modelLogisticRegression,10)
rfelogisticReg=rfelogisticReg.fit(X_train, y_train)
print("Feature Importance of Logistic Regression Model")
print(rfelogisticReg.support_)
print(rfelogisticReg.ranking_)
modelLogisticRegression.fit(X_train, y_train)
return modelLogisticRegression
def select_features(X, y, clf=None, n_features=10):
if not clf:
clf = LogisticRegression()
clf.fit(X, y)
selector = RFE(clf, n_features_to_select=n_features)
selector = selector.fit(X, y)
features = np.array(range(57))
# print selector.ranking_
# print selector.support_
return features[selector.support_]
#########################
transfomers = [DummyTransformer, Normalizer(), StandardScaler()]
transfomers_cfg = {}
transfomers_cfg[DummyTransformer.func.__name__] = {}
transfomers_cfg[Normalizer.__name__] = dict(
transfomer__norm=['l1', 'l2', 'max'])
transfomers_cfg[StandardScaler.__name__] = {}
###########################
####Dim Reducer, Feat Sel.#
###########################
reducers = [
DummyTransformer,
PCA(),
GenericUnivariateSelect(),
RFE(ExtraTreesRegressor())
]
reducers_cfg = {}
reducers_cfg[DummyTransformer.func.__name__] = {}
reducers_cfg[PCA.__name__] = dict(
reducer__n_components=[],
# reducer__whiten = [True, False],
reducer__svd_solver=['auto'])
reducers_cfg[GenericUnivariateSelect.__name__] = dict(
reducer__score_func=[f_regression],
reducer__mode=['k_best'],
reducer__param=[])
reducers_cfg[RFE.__name__] = dict(reducer__n_features_to_select=[],
reducer__step=[0.1])
#########################
####### Models ##########
# param_grid=param_grid,
# scoring='accuracy',
# cv=10,
# n_jobs=-1)
# pred = estimators[k].predict(X_test)
# print("%s Score: %0.02f" % (k, estimators[k].score(X_test, y_test)))
# scores = cross_validation.cross_val_score(estimators[k], X, y, cv=5)
# print("%s Cross Avg. Score: %0.02f (+/- %0.02f)" % (k, scores.mean(), scores.std() * 2))
# end_time = datetime.datetime.now()
# time_spend = end_time - start_time
# print("%s Time: %0.02f" % (k, time_spend.total_seconds()))
from sklearn.feature_selection import RFE
rfe = RFE(clf, 41)
clf1 = rfe.fit(X, y)
clf1.score(X, y)
yhat_test = clf1.predict_proba(X_test)
clf1.score(X_test, y_test)
#conduct grid search for the models:
#logistic regression
from sklearn.grid_search import GridSearchCV
param_range = [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0]
tuned_parameters = [{'C': param_range}]
scores = ['precision', 'recall']
for score in scores:
print("# Tuning hyper-parameters for %s" % score)
# ### Fit a logistic regression model
# In[14]:
lgr = LogisticRegression(C=5)
lgr.fit(X,y)
# ### Select best features using RFE feature selection
# In[42]:
from sklearn.feature_selection import RFE
selector = RFE(lgr, 20)
selector.fit_transform(X, y)
ranks = selector.ranking_
X_names = encoded_df.columns.drop('good_bad')
# print sorted(map(lambda x: round(x, 4), selector.ranking_), names)
# In[110]:
rfe_features = np.column_stack((X_names, ranks))
rfe_cols = rfe_features[np.where(rfe_features[:,1]<10),:2][0]
rfe_col1 = rfe_cols[:,:1]
print(rfe_col1)
#testFeatures, testLabels = transformDataset(test_sents)
corpus=[d for (d,c) in documents]
labels=[c for (d,c) in documents]
features=tfidf(corpus)
#print(features[1])
#features,labels=transformDataset(documents)
#vec = DictVectorizer()
#features_new=vec.fit_transform(features).toarray()
#print(features_new.shape)
print(len(features))
print(len(labels))
svc = SVC(kernel="linear", C=1)
clf = RFE(svc, 300, step=1)
fe = clf.fit_transform(features, labels)
#print(fit.scores_)
print(fe.shape)
# summarize selected features
trainFeatures, testFeatures, trainLabels, testLabels = train_test_split(fe,labels, test_size=0.33, random_state=42)
print("length of testLabels=",len(testLabels))
#for l in testLabels:
# print("label=",l)
#print("features=",trainFeatures[1],"label=",trainLabels[1])
#featuresets = [(document_features(d), c) for (d,c) in documents]
var = 1
def classify_one_vs_many(df,
model_name,
model,
feature_to_class,
type_class,
type_0_class=None):
GH_df_reduced_one_vs_many = df.copy()
if type_0_class is None:
others_df = GH_df_reduced_one_vs_many[(
GH_df_reduced_one_vs_many[feature_to_class] != type_class)].copy()
others_df.loc[:, 'ml_type'] = type_0_class = 'others'
else:
others_df = GH_df_reduced_one_vs_many[(
GH_df_reduced_one_vs_many[feature_to_class] == type_0_class
)].copy()
others_df.loc[:, 'ml_type'] = type_0_class
category_df = GH_df_reduced_one_vs_many[
GH_df_reduced_one_vs_many[feature_to_class] == type_class].copy()
category_df.loc[:, 'ml_type'] = type_class
df_merged = pd.concat([others_df, category_df], ignore_index=True)
# print df_merged.groupby(['ml_type','category'])['analizo_accm_mean'].count()
X = df_merged.select_dtypes(include=[np.number])
y = df_merged.loc[:, 'ml_type']
test_size = 0.2
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=test_size)
ros = RandomOverSampler(random_state=0)
if len(y_train.unique()) < 2:
print('cannot fit for {}'.format(type_class))
return None
X_resampled, Y_resampled = ros.fit_resample(X_train, y_train)
# print('Training target statistics: {}'.format(Counter(y)))
if Counter(y)[type_class] == 1:
print('cannot fit for {}'.format(type_class))
return
model.fit(X_train, y_train)
# print model.score(X_test,y_test)
rfe = RFE(model, 4)
fit = rfe.fit(X_train, y_train)
# print "Selected features : " + str(X.columns[fit.support_])
pred = model.predict(X_test)
# print Counter(pred)
# df_accurarcy = set_wrong_type(pred,y, df_merged,type_class)
# calculate_accurarcy(df_accurarcy,pred,y,type_class)
fpr = tpr = roc_auc = None
t = True
try:
y_pred = model.predict_proba(X_test)[:, 1]
except:
t = False
if t:
fpr, tpr, _ = roc_curve(y_test, y_pred, pos_label=type_class)
roc_auc = auc(tpr, fpr)
f1 = f1_score(y_test, pred, pos_label=type_class)
return {
'model_name': model_name,
'agent_type': agent_type,
'feature_importance': fit,
'model': model,
'fpr': fpr,
'tpr': tpr,
'auc': roc_auc,
'f1_score': f1,
'class 0': type_0_class,
'class 1': type_class
}
def main(training_input_path, testing_input_path, output_path):
# LOAD DATA
train = pd.read_csv(training_input_path, header=0)
test = pd.read_csv(testing_input_path, header=0)
# PREPROCESSING
le = LabelEncoder()
train["ocean_proximity"] = le.fit_transform(train["ocean_proximity"])
test["ocean_proximity"] = le.transform(test["ocean_proximity"])
# SPLIT TRAINING AND TESTING DATA INTO X AND Y
X_train = train.drop(columns="median_house_value")
y_train = train['median_house_value']
X_test = test.drop(columns="median_house_value")
y_test = test['median_house_value']
# CREATE A DF THAT EXCLUDES LATITUDE AND LONGITUDE
X_train_featexc = X_train.drop(columns=["latitude", "longitude"])
X_test_featexc = X_test.drop(columns=["latitude", "longitude"])
# CREATE A DF THAT EXCLUDES LATITUDE, LONGITUDE, AND TOTAL BEDROOMS
X_train_featexc_2 = X_train.drop(
columns=["latitude", "longitude", "total_bedrooms"])
X_test_featexc_2 = X_test.drop(
columns=["latitude", "longitude", "total_bedrooms"])
# APPLY SCALER
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
X_train_featexc = scaler.fit_transform(X_train_featexc)
X_test_featexc = scaler.transform(X_test_featexc)
X_train_featexc_2 = scaler.fit_transform(X_train_featexc_2)
X_test_featexc_2 = scaler.transform(X_test_featexc_2)
# LINEAR REGRESSION WITH FEATURE SELECTION - ALL FEATURES AVAILABLE
lr_response = {
'n_features_to_select': [],
'train_error': [],
'test_error': []
}
for i in list(range(1, X_train.shape[1] + 1, 1)):
lr_response['n_features_to_select'].append(i)
rfe_lr = RFE(LinearRegression(), n_features_to_select=i)
rfe_lr.fit(X_train, y_train)
lr_response['train_error'].append(
round(1 - rfe_lr.score(X_train, y_train), 3))
lr_response['test_error'].append(
round(1 - rfe_lr.score(X_test, y_test), 3))
pd.DataFrame(lr_response).to_csv(output_path + 'lr_rfe_results_table.csv',
index=False)
# Plotting LR performance
data = pd.DataFrame(lr_response).melt(
id_vars='n_features_to_select',
value_vars=['train_error', 'test_error'])
plot = alt.Chart(data).mark_line().encode(
x=alt.X('n_features_to_select:Q', title="Number of Features Selected"),
y=alt.Y('value:Q', title="Error"),
color=alt.Color('variable:N', title="Data Split")).properties(
title="Recursive Feature Elimination Linear Regression Error",
width=250,
height=200)
plot.save(output_path + 'LR_performace.png')
# LINEAR REGRESSION WITH FEATURE SELECTION - EXCLUDING LATITUDE AND LONGITUDE
lr_response_exc = {
'n_features_to_select': [],
'train_error': [],
'test_error': []
}
for i in list(range(1, X_train_featexc.shape[1] + 1, 1)):
lr_response_exc['n_features_to_select'].append(i)
rfe_lr = RFE(LinearRegression(), n_features_to_select=i)
rfe_lr.fit(X_train_featexc, y_train)
lr_response_exc['train_error'].append(
round(1 - rfe_lr.score(X_train_featexc, y_train), 3))
lr_response_exc['test_error'].append(
round(1 - rfe_lr.score(X_test_featexc, y_test), 3))
pd.DataFrame(lr_response_exc).to_csv(output_path +
'lr_rfe_results_table_exc_feats.csv',
index=False)
# Plotting LR performance excluding latitude and longitude
data = pd.DataFrame(lr_response_exc).melt(
id_vars='n_features_to_select',
value_vars=['train_error', 'test_error'])
plot = alt.Chart(data).mark_line().encode(
x=alt.X('n_features_to_select:Q', title="Number of Features Selected"),
y=alt.Y('value:Q', title="Error"),
color=alt.Color('variable:N', title="Data Split")
).properties(
title=
"Recursive Feature Elimination Linear Regression Error Excluding Latitude and Longitude",
width=250,
height=200)
plot.save(output_path + 'LR_performace_exc_feats.png')
# LINEAR REGRESSION WITH FEATURE SELECTION - EXCLUDING LATITUDE, LONGITUDE, AND TOTAL BEDROOMS
lr_response_exc_2 = {
'n_features_to_select': [],
'train_error': [],
'test_error': []
}
for i in list(range(1, X_train_featexc_2.shape[1] + 1, 1)):
lr_response_exc_2['n_features_to_select'].append(i)
rfe_lr = RFE(LinearRegression(), n_features_to_select=i)
rfe_lr.fit(X_train_featexc_2, y_train)
lr_response_exc_2['train_error'].append(
round(1 - rfe_lr.score(X_train_featexc_2, y_train), 3))
lr_response_exc_2['test_error'].append(
round(1 - rfe_lr.score(X_test_featexc_2, y_test), 3))
pd.DataFrame(lr_response_exc_2).to_csv(
output_path + 'lr_rfe_results_table_exc_feats_2.csv', index=False)
# Plotting LR performance excluding latitude and longitude
data = pd.DataFrame(lr_response_exc_2).melt(
id_vars='n_features_to_select',
value_vars=['train_error', 'test_error'])
plot = alt.Chart(data).mark_line().encode(
x=alt.X('n_features_to_select:Q', title="Number of Features Selected"),
y=alt.Y('value:Q', title="Error"),
color=alt.Color('variable:N', title="Data Split")
).properties(
title=
"Recursive Feature Elimination Linear Regression Error Excluding Latitude, Longitude, and Total Bedrooms",
width=250,
height=200)
plot.save(output_path + 'LR_performace_exc_feats_2.png')
# KNN WITH VARYING N_NEIGHBOR VALUES WITH FULL DATA INCLUSION
knn_response = {'n_neighbours': [], 'train_error': [], 'test_error': []}
for i in list(range(1, 20, 1)):
knn_response['n_neighbours'].append(i)
knn = KNeighborsRegressor(n_neighbors=i)
knn.fit(X_train, y_train)
knn_response['train_error'].append(
round(1 - knn.score(X_train, y_train), 3))
knn_response['test_error'].append(
round(1 - knn.score(X_test, y_test), 3))
predictions = knn.predict(X_test)
pd.DataFrame(knn_response).to_csv(output_path + 'knn_results_table.csv',
index=False)
# ploting KNN performance
data = pd.DataFrame(knn_response).melt(
id_vars='n_neighbours', value_vars=['train_error', 'test_error'])
plot = alt.Chart(data).mark_line().encode(
x=alt.X('n_neighbours:Q', title="Number of Nearest Neighbours"),
y=alt.Y('value:Q', title="Error"),
color=alt.Color('variable:N', title="Data Split")).properties(
title="K-Nearest Neighbour Error when Varying K",
width=250,
height=200)
plot.save(output_path + 'KNN_performace.png')
# plotting KNN performance compared to actual values
pred_estimates = pd.merge(
pd.DataFrame(y_test),
pd.DataFrame(predictions),
left_index=True,
right_index=True).rename(columns={
0: "prediction",
"median_house_value": "actual"
})
pred_estimates = pd.melt(pred_estimates,
value_vars=['actual', 'prediction'])
plot = alt.Chart(pred_estimates).mark_bar(opacity=0.3).encode(
alt.X('value:Q', bin=alt.Bin(maxbins=40), title="Median House Value"),
alt.Y('count()', stack=None, title="Count"),
alt.Color('variable', title="Value")).properties(
title="Histogram of Actual and Predicted Median House Values",
width=400,
height=200)
plot.save(output_path + 'KNN_actual_vs_predicted.png')
# KNN WITH VARYING N_NEIGHBOR VALUES WITH LATITUDE AND LONGITUDE EXCLUSION
knn_response_exc = {
'n_neighbours': [],
'train_error': [],
'test_error': []
}
for i in list(range(1, 20, 1)):
knn_response_exc['n_neighbours'].append(i)
knn_exc = KNeighborsRegressor(n_neighbors=i)
knn_exc.fit(X_train_featexc, y_train)
knn_response_exc['train_error'].append(
round(1 - knn_exc.score(X_train_featexc, y_train), 3))
knn_response_exc['test_error'].append(
round(1 - knn_exc.score(X_test_featexc, y_test), 3))
predictions = knn_exc.predict(X_test_featexc)
pd.DataFrame(knn_response_exc).to_csv(output_path +
'knn_results_table_exc_feats.csv',
index=False)
# ploting KNN performance
data = pd.DataFrame(knn_response_exc).melt(
id_vars='n_neighbours', value_vars=['train_error', 'test_error'])
plot = alt.Chart(data).mark_line().encode(
x=alt.X('n_neighbours:Q', title="Number of Nearest Neighbours"),
y=alt.Y('value:Q', title="Error"),
color=alt.Color('variable:N', title="Data Split")
).properties(
title=
"K-Nearest Neighbour Error when Varying K and Excluding Latitude and Longitude",
width=250,
height=200)
plot.save(output_path + 'KNN_performace_exc_feats.png')
# plotting KNN performance compared to actual values excluding latitude and longitude
pred_estimates = pd.merge(
pd.DataFrame(y_test),
pd.DataFrame(predictions),
left_index=True,
right_index=True).rename(columns={
0: "prediction",
"median_house_value": "actual"
})
pred_estimates = pd.melt(pred_estimates,
value_vars=['actual', 'prediction'])
plot = alt.Chart(pred_estimates).mark_bar(opacity=0.3).encode(
alt.X('value:Q', bin=alt.Bin(maxbins=40), title="Median House Value"),
alt.Y('count()', stack=None, title="Count"),
alt.Color('variable', title="Value")
).properties(
title=
"Histogram of Actual and Predicted Median House Values Excluding Latitude and Longitude",
width=400,
height=200)
plot.save(output_path + 'KNN_actual_vs_predicted_exc_feats.png')
# RANDOM FOREST REGRESSOR
rfr = RandomForestRegressor(random_state=522)
gs = GridSearchCV(rfr,
param_grid={
"max_depth": np.arange(5, 10, 1),
"min_samples_leaf": np.arange(1, 4, 1)
})
gs.fit(X_train, y_train)
rfr = gs.best_estimator_
rfr_response = {
'type': ['Random Forest Regressor'],
'train_error': [round(1 - rfr.score(X_train, y_train), 3)],
'test_error': [round(1 - rfr.score(X_test, y_test), 3)]
}
pd.DataFrame(rfr_response).to_csv(output_path + 'rfr_results_table.csv',
index=False)
# TESTING
assert os.path.isfile(output_path + 'rfr_results_table.csv')
assert os.path.isfile(output_path + 'KNN_performace.png')
assert os.path.isfile(output_path + 'lr_rfe_results_table.csv')
assert os.path.isfile(output_path + 'LR_performace.png')
assert os.path.isfile(output_path + 'rfr_results_table.csv')
assert os.path.isfile(output_path + 'knn_results_table_exc_feats.csv')
assert os.path.isfile(output_path + 'KNN_performace_exc_feats.png')
assert os.path.isfile(output_path + 'lr_rfe_results_table_exc_feats.csv')
assert os.path.isfile(output_path + 'LR_performace_exc_feats.png')
assert os.path.isfile(output_path + 'lr_rfe_results_table_exc_feats_2.csv')
assert os.path.isfile(output_path + 'LR_performace_exc_feats_2.png')
assert os.path.isfile(output_path + 'KNN_actual_vs_predicted.png')
assert os.path.isfile(output_path +
'KNN_actual_vs_predicted_exc_feats.png')
for o in range(0, 10):
#split into test and train set
F_Training_Train, F_Training_Test, Label_Training_Train, Label_Training_Test = train_test_split(
features_training, label_training, test_size=0.33)
F_Test_Train, F_Test_Test, Label_Test_Train, Label_Test_Test = train_test_split(
features_test, label_test, test_size=0.70)
#classification
# clf = SVC(kernel='linear')
# clf = LogisticRegression()
# clf = RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)
clf = GradientBoostingClassifier()
#recursive feature elimination
selector = RFE(clf, 1, step=1)
Label_train = np.ravel(Label_Training_Train)
Label_test = np.ravel(Label_Test_Test)
selector = selector.fit(F_Training_Train, Label_train)
rank = selector.ranking_
Rank.append(rank)
rank = np.asarray(rank)
#create a list that contains index numbe of ranked features
rankedlist = np.zeros((7, 1))
#finding index of the ranked features and creating new training and test sets with respect to this ranking
for m in range(1, 8):
k = np.where(rank == m)
rankedlist[m - 1] = k[0][0]
F_Training_Train[:,
# acc = accuracy_score(y_test, y_pred)
# print("Accuracy: {:.4%}".format(acc))
# print(classification_report(y_test, y_pred, digits=4))
seeds = 1618 # Регулируем значения псевдогенератора случайных чисел
confusion_matrixs = []
# ОТБОР ПРИЗНАКОВ. Метод 1
model = ExtraTreesClassifier(random_state=seeds)
model.fit(x_tr, y_tr)
print(model.feature_importances_)
# ОТБОР ПРИЗНАКОВ. Метод 2
model = LogisticRegression(random_state=seeds)
# create the RFE model and select 3 attributes
rfe = RFE(model, 2)
rfe = rfe.fit(x_tr, y_tr)
print(rfe.support_)
print(rfe.ranking_)
# Оба метода отбора признаков говорят о минимальном вкладе 2 и 4 компоненты.
# Для текущего этапа(классификация первого столбца в справочнике). Можно их исключить, но у меня не так много признаков. Пока оставим.
seeds = 1618 # Регулируем значения псевдогенератора случайных чисел
''' ==> ЛОГИСТИЧЕСКАЯ РЕГРЕССИЯ
'''
# Часто используется для задач бинарной классификации, но допускается и многоклассовая классификация методом "one-vs-all".
# Достоинством этого алгоритма являеся то, что на выходе для каждого обьекта мы имеем вероятсность принадлежности классу.
model = LogisticRegression(random_state=1618, solver='lbfgs')
model.fit(x_tr, y_tr)
# print(cor_feature) from sklearn.feature_selection import SelectKBest from sklearn.feature_selection import chi2 from sklearn.preprocessing import MinMaxScaler X_norm = MinMaxScaler().fit_transform(X) chi_selector = SelectKBest(chi2, k=num_feats) chi_selector.fit(X_norm, y) chi_support = chi_selector.get_support() chi_feature = X.loc[:,chi_support].columns.tolist() print(str(len(chi_feature)), 'selected features') from sklearn.feature_selection import RFE from sklearn.linear_model import LogisticRegression rfe_selector = RFE(estimator=LogisticRegression(max_iter=1000), n_features_to_select=num_feats, step=10, verbose=5) rfe_selector.fit(X_norm, y) rfe_support = rfe_selector.get_support() rfe_feature = X.loc[:,rfe_support].columns.tolist() print(str(len(rfe_feature)), 'selected features') from sklearn.feature_selection import SelectFromModel from sklearn.linear_model import LogisticRegression embeded_lr_selector = SelectFromModel(LogisticRegression(solver='saga', penalty="l1", max_iter=1000), max_features=num_feats) embeded_lr_selector.fit(X_norm, y) embeded_lr_support = embeded_lr_selector.get_support() embeded_lr_feature = X.loc[:,embeded_lr_support].columns.tolist() print(str(len(embeded_lr_feature)), 'selected features')
'''
print('--FEATURE SELECTION ON--', '\n')
##1) Run Feature Selection #######
if fs_type == 1:
#Stepwise Recursive Backwards Feature removal
if binning == 0:
clf = DecisionTreeClassifier(criterion='gini',
splitter='best',
max_depth=None,
min_samples_split=3,
min_samples_leaf=1,
max_features=None,
random_state=rand_st)
sel = RFE(clf, n_features_to_select=k_cnt, step=.1)
print('Stepwise Recursive Backwards - Random Forest: ')
if binning == 1:
rgr = DecisionTreeClassifier(criterion='gini',
splitter='best',
max_depth=None,
min_samples_split=3,
min_samples_leaf=1,
max_features=None,
random_state=rand_st)
sel = RFE(rgr, n_features_to_select=k_cnt, step=.1)
print('Stepwise Recursive Backwards - Random Forest: ')
fit_mod = sel.fit(data_np, target_np)
print(sel.ranking_)
sel_idx = fit_mod.get_support()
colname=loan_train.columns[:]
colname
from sklearn import tree
with open(r"XYZCorp_LendingData.txt", "w") as f:
f = tree.export_graphviz(model_Decision_tree, feature_names= colname[:-1],out_file=f)
#generate the file and upload the code in webgraphviz.com to plot the decision tree
# feature importance attribute of decision tree
print(list(zip(colname,model_Decision_tree.feature_importances_)))
from sklearn.feature_selection import RFE
rfe = RFE(classifier, 20)
model_rfe = rfe.fit(X_train, Y_train)
print("Num Features: ",model_rfe.n_features_)
print("Selected Features: ")
print(list(zip(loan_train.columns, model_rfe.support_)))
print("Feature Ranking: ", model_rfe.ranking_)
Y_pred=model_rfe.predict(X_test)
#predicting using the Random_Forest_Classifier
from sklearn.ensemble import RandomForestClassifier
model_RandomForest=RandomForestClassifier(500)
###
for val in l[:-1]:
j += 1
data[i][j] = float(val)
X, y = data[:, :-1], data[:, -1]
#y = np.array([y])
#y = np.reshape(y,(y.shape[1],y.shape[0]))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
stratify=y,
random_state=42)
clf = SVC(gamma='auto', kernel='linear')
selector = RFE(clf, 100, step=1)
selector = selector.fit(X_train, y_train)
y_pred = selector.estimator_.predict(X_test.compress(selector.support_,
axis=1))
curr_pos = curr_neg = inc_pos = inc_neg = 0
for i in range(len(y_test)):
if y_test[i] == 1:
if y_pred[i] == 1:
curr_pos += 1
else:
inc_neg += 1
else:
if y_pred[i] == 1:
##Link https://medium.com/@aneesha/recursive-feature-elimination-with-scikit-learn-3a2cbdf23fb7
# Feature Extraction with RFE
from pandas import read_csv
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
# load data
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
names = [
'preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'
]
dataframe = read_csv(url, names=names)
array = dataframe.values
X = array[:, 0:8]
Y = array[:, 8]
# feature extraction
model = LogisticRegression()
rfe = RFE(model, 3)
fit = rfe.fit(X, Y)
print("Num Features: %d") % fit.n_features_
print("Selected Features: %s") % fit.support_
print("Feature Ranking: %s") % fit.ranking_
model = LogisticRegression(solver='lbfgs', max_iter=500)
for i in range(1, df_X.shape[1]+1):
fs = sorted_columns[0:i]
df_X_selected = df_X[fs]
scores = cross_val_score(model, df_X_selected, df_y, cv=5)
print(fs.tolist())
print(np.round(scores.mean(), 4))
######################################################################
# Backward elimination (Recursive Feature Elimination)
######################################################################
from sklearn.feature_selection import RFE
model = LogisticRegression(solver='lbfgs', max_iter=500)
rfe = RFE(model, n_features_to_select=4)
fit = rfe.fit(df_X, df_y)
print("Num Features: %d" % fit.n_features_)
fs = df_X.columns[fit.support_].tolist() # selected features
print("Selected Features: %s" % fs)
#print("Feature Ranking: %s" % fit.ranking_)
scores = cross_val_score(model, df_X[fs], df_y, cv=5)
print("Acc: "+str(scores.mean()))
######################################################################
# Forward selection
######################################################################
# please install 'mlxtend' moudle
from mlxtend.feature_selection import SequentialFeatureSelector as SFS
plt.xlabel('Feature1')
plt.ylabel('Frequency of Feature1')
plt.show()
plt.savefig('Frequency of Feature1')
#Feature Selection
data_final_vars = data.columns.values.tolist()
y = ['Sickness', 'ID']
Y = ['Sickness']
X = [i for i in data_final_vars if i not in y]
print(X, y)
logreg = LogisticRegression()
rfe = RFE(logreg, 20)
rfe = rfe.fit(data[X], data[Y])
print(rfe.support_)
print(rfe.ranking_)
cols = [
"Feature15",
"Feature23",
"Feature43",
"Feature45",
"Feature64",
"Feature87",
"Feature115",
"Feature127",
"Feature162",
"Feature163",
for rfe_step_idx, rfe_step in enumerate(rfe_step_range):
print(
str(count_iter) + '/' + str(
len(seed_range) * len(nCoeffs_range) *
len(rfe_step_range)))
for train_index, test_index in skf.split(features,
labels): # external CV
X_train, X_test = features[train_index], features[test_index]
y_train, y_test = labels[train_index], labels[test_index]
scaler = MinMaxScaler()
sv = LinearSVC()
rfe = RFE(sv, step=rfe_step, n_features_to_select=nCoeffs)
# Defining scaler + rfe
pipe = Pipeline([('std_scaler', scaler), ('fs', rfe)])
clf = GridSearchCV(pipe,
param_grid=param_grid,
cv=inner_folds,
scoring=scoring_fct,
n_jobs=6)
y_score = clf.fit(X_train, y_train)
#print(clf.best_params_)
best_model = clf.best_estimator_
selector = best_model.named_steps['fs']
pd.DataFrame(np.transpose(classifier.coef_), columns = ["coef"])
],axis = 1)
#### Feature Selection ####
## Feature Selection
# Recursive Feature Elimination
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
# Model to Test
classifier = LogisticRegression()
# Select Best X Features
rfe = RFE(classifier, 20)
rfe = rfe.fit(X_train, y_train)
# summarize the selection of the attributes
print(rfe.support_)
print(rfe.ranking_)
X_train.columns[rfe.support_]
# New Correlation Matrix
sn.set(style="white")
# Compute the correlation matrix
corr = X_train[X_train.columns[rfe.support_]].corr()
# Generate a mask for the upper triangle
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
return np.amax([val1, val2])
# K=2 TITANIC
pca_titanic = []
ica_titanic = []
rca_titanic = []
rfe_titanic = []
k=2
for dim in range(1, len(tit_cols)+1):
pca = PCA(n_components=dim)
ica = FastICA(n_components=dim)
rca = GaussianRandomProjection(n_components=dim)
logreg = LogisticRegression()
rfe = RFE(logreg, n_features_to_select=dim)
pca_X_train = pca.fit_transform(tit_X_train)
ica_X_train = ica.fit_transform(tit_X_train)
rca_X_train = rca.fit_transform(tit_X_train)
rfe.fit(tit_X_train, tit_y_train)
rfe_X_train = rfe.transform(tit_X_train)
em = GaussianMixture(n_components=k)
em.fit(pca_X_train)
pca_em_X_train = em.predict(pca_X_train)
em.fit(ica_X_train)
ica_em_X_train = em.predict(ica_X_train)
em.fit(rca_X_train)
rca_em_X_train = em.predict(rca_X_train)
em.fit(rfe_X_train)
rfe_em_X_train = em.predict(rfe_X_train)
print("finish")
names = [
'alloy', 'class', 'delta', 'Hmix', 'Smix', 'Fi', 'RMS', 'VEC', 'r', 'Sc',
'deltaHmixmax', 'deltaHmixmin', 'rootHmix', 'rootHmix0', 'rootHmix0+',
'rootHmix0-'
]
data = pd.read_csv('合并数据集-去除重复.csv', header=0, names=names)
Y = data[["class"]]
X = pd.read_csv('generate_feature_1008.csv')
print("finish")
rfc = RandomForestClassifier()
#Y=Y.values
#Y= Y.reshape(c, )
rfe = RFE(estimator=rfc, n_features_to_select=1, step=1)
rfe.fit(X, Y)
ranking = rfe.ranking_
print("RFE ranking:\n", ranking)
list_ranking_index = []
list_ranking_importance = []
for i in range(len(ranking)):
if ranking[i] <= 100:
list_ranking_index.append(i)
list_ranking_importance.append(ranking[i])
print("list_ranking_index:\n", list_ranking_index)
print("list_ranking_importance:\n", list_ranking_importance)
print('finish')
#写入CSV
def RFE(self,estimator,k):
X=self.X
Y=self.Y
rfe=RFE(estimator,n_features_to_select=k)
res=rfe.fit_transform(X,Y)
return rfe,res
X_train=training_data[['X1','X2','X3','X4','X5','X6','X7','X8']]
y_train=training_data[['Y']]
# step-1: create a cross-validation scheme
folds = KFold(n_splits = 10, shuffle = True, random_state = 100)
# step-2: specify range of hyperparameters to tune
hyper_params = [{'n_features_to_select': list(range(1, 9))}]
# step-3: perform grid search
# 3.1 specify model
lm = LinearRegression()
rfe = RFE(lm)
# 3.2 call GridSearchCV()
model_cv = GridSearchCV(estimator = rfe,
param_grid = hyper_params,
scoring= 'r2',
cv = folds,
verbose = 1,
return_train_score=False)
lr= model_cv.fit(X_train,y_train)
y_predict=lr.predict(X_train)
print("The coefficient of determination(r squared) obtained from Linear Regression:\n")
######score here returns The coefficient of determination(r squared) the closer to 1 the better model
print(lr.score(X_train,y_train),"\n")
# for p in cv:
# print p
# print len(cv)
# sys.exit()
''' Logistic regression '''
# w = 'balanced'
# clf = LogisticRegression(class_weight=w, penalty='l1', n_jobs=1)
# parameters = {'C': np.hstack((np.arange(0.0095, 0.02, 0.0001), np.arange(0.02, 0.601, 0.005)))}
# parameters = {'C': [0.005, 0.0075, 0.01]}
# parameters = {'C': [0.005]}
clf = Pipeline([
# ('rfe', RFE(estimator=LogisticRegression(class_weight='balanced', penalty='l1', C=0.01), n_features_to_select=2,
('rfe', RFE(estimator=LogisticRegression(class_weight='balanced', penalty='l1', C=0.001), n_features_to_select=2,
step=0.1)),
('clf', LogisticRegression(class_weight='balanced', penalty='l1', n_jobs=1))
])
# parameters = {'clf__C': [0.005, 0.0075, 0.01]}
parameters = {'clf__C': [0.001, 0.01]}
K = 5
R = 1 # repeat cross-validation
auc_limit = 0.55
auc_hat = 1
step_remove = 1
# TODO
# TODO
os_data_X,os_data_y=os.fit_sample(X_train, y_train)
os_data_X = pd.DataFrame(data=os_data_X,columns=columns )
os_data_y= pd.DataFrame(data=os_data_y,columns=['IntermittentIceCover'])
# we can Check the numbers of our data
print("length of oversampled data is ",len(os_data_X))
print("Number of annual lakes",len(os_data_y[os_data_y['IntermittentIceCover']==0]))
print("Number of intermittent lakes",len(os_data_y[os_data_y['IntermittentIceCover']==1]))
print("Proportion of annual lakes in oversampled data is ",len(os_data_y[os_data_y['IntermittentIceCover']==0])/len(os_data_X))
print("Proportion of intermittent lakes in oversampled data is ",len(os_data_y[os_data_y['IntermittentIceCover']==1])/len(os_data_X))
dt_vars=dt.columns.values.tolist()
y=['IntermittentIceCover']
X=[i for i in dt_vars if i not in y]
logreg = LogisticRegression()
rfe = RFE(logreg, 20)
rfe = rfe.fit(os_data_X, os_data_y.values.ravel())
print(rfe.support_)
print(rfe.ranking_)
cols=[ "MeanAnnualAirTemp_c", "MaximumDepth_m", 'Latitude_dd', 'temp_range']
#cols=[ "Elevation_m", "MeanAnnualAirTemp_c", "MaximumDepth_m", 'Latitude_dd']
X=os_data_X[cols]
y=os_data_y['IntermittentIceCover']
logit_model=sm.Logit(y,X)
result=logit_model.fit()
print(result.summary2())
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=4)
def train_svm_k_fold_RFE(matrix,
target,
gamma,
linear=True,
nfeatures=15,
nsplits=10,
penalty="l2",
C=1,
multi_class="ovr",
kernel="rbf",
degree=3,
probability=False,
decision_function_shape="ovr"):
scores = []
confusion = []
features = []
parameters = {
"Gamma": gamma,
"Linear": linear,
"C": C,
"Kernel": kernel,
"Degree": degree,
"Average": [],
"Scores": [],
"Features": [],
"Macro": [],
"Micro": [],
"Weighted": []
}
if (linear):
best_svc = LinearSVC(penalty="l2", C=C, multi_class="ovr")
else:
best_svc = SVC(C=C,
kernel=kernel,
gamma=gamma,
degree=degree,
probability=probability,
decision_function_shape=decision_function_shape)
cv = KFold(n_splits=nsplits, random_state=42, shuffle=False)
for train_index, test_index in cv.split(matrix):
#print("Train Index: ", train_index, "\n")
#print("Test Index: ", test_index)
X_train, X_test, y_train, y_test = matrix[train_index], matrix[
test_index], target[train_index], target[test_index]
# ---------------- FEATURE SELECTION ------------------------
rforest = RandomForestClassifier(random_state=101)
rfe = RFE(estimator=rforest, n_features_to_select=nfeatures)
rfe.fit(X_train, y_train)
support = rfe.support_
j = 0
indexes = []
for i in support:
if i == True:
indexes.append(j)
j += 1
x_train_fs = X_train[:, indexes]
# --------------- TRAINING ------------------------------
# Training the model
best_svc.fit(x_train_fs, y_train)
#--------------- TESTING -------------------------------
# Getting the scores of the model on the test set
svc_predictions = best_svc.predict(X_test[:, indexes])
# getting accuracy
scores.append(best_svc.score(X_test[:, indexes], y_test))
# Macro
parameters["Macro"].append(
precision_recall_fscore_support(y_test,
svc_predictions,
average='macro'))
# Micro
parameters["Micro"].append(
precision_recall_fscore_support(y_test,
svc_predictions,
average='micro'))
# Weighted
parameters["Weighted"].append(
precision_recall_fscore_support(y_test,
svc_predictions,
average='weighted'))
parameters["Features"].append(indexes)
# getting confusion matrix
confusion.append(confusion_matrix(y_test, svc_predictions))
parameters["Scores"].append(scores)
parameters["Average"] = np.average(scores)
return (scores, confusion, parameters)
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.model_selection import (cross_val_score, KFold, cross_validate,
train_test_split)
from sklearn.ensemble import StackingClassifier
data = load_wine()
y = data.target
X = data.data
stc = StandardScaler()
lenc = LabelEncoder()
columns = data.feature_names
df = pd.DataFrame(data=np.hstack(tup=(X, y.reshape(-1, 1))),
columns=np.hstack(tup=(columns, ["Class"])))
X_std = stc.fit_transform(df[columns])
pipesvm = Pipeline([("stc", stc), ("selection", RFE(LinearSVC())),
("svm", SVC(kernel="linear"))])
pipelda = Pipeline([("stc", stc), ("svm", LinearDiscriminantAnalysis())])
estimators = [("LDA", pipelda), ("SVM", pipesvm)]
# El utilizar clasificadores apilados tiene beneficios cuando se trata de
# problemas multiclase, puesto que puede mejorar mucho el pronostico de clase
# al explotar el poder predictivo del pronostico para ciertas clases
stacking_classifier = StackingClassifier(estimators=estimators,
final_estimator=GaussianNB())
print("Stacking stimators")
print(
cross_val_score(X=df[columns],
y=y,
estimator=stacking_classifier,
cv=KFold(5)))
print("Only SVM")
del X['target']
del X['id']
X.describe()
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
le.fit(Y.values.tolist())
label = le.transform(Y)
print(list(le.classes_))
print(label)
noOfFeature = 45
from sklearn.feature_selection import RFE
from sklearn.ensemble import RandomForestClassifier
import timeit
start = timeit.default_timer()
clf = RandomForestClassifier()
rfe = RFE(clf, noOfFeature)
fit = rfe.fit(X, label)
print("Time take %.2f " % (timeit.default_timer() - start))
print(("Num Features: %d") % fit.n_features_)
print(("Selected Features: %s") % fit.support_)
print(("Feature Ranking: %s") % fit.ranking_)
features = []
for i, j in zip(X.columns, fit.support_):
if j == True:
features.append(str(i))
print(features)
from sklearn.model_selection import cross_val_score
import timeit
from xgboost import XGBClassifier
from statistics import mean
train_csv = pd.read_csv('../input/train.csv')
X = fifa.drop('Overall', 1)
y = fifa['Overall']
lr_model = LinearRegression()
rfe = RFE(lr_model, n_features_to_select=5)
rfe.fit(X, y)
mask = rfe.support_
top_features = X.columns[mask]
return list(top_features)
# In[117]:
q4()
# In[118]:
X = fifa.drop('Overall', 1)
y = fifa['Overall']
lr_model = LinearRegression()
rfe = RFE(lr_model, n_features_to_select=5)
rfe.fit(X, y)
plt.figure()
plt.title("Feature Importance")
pd.Series(rfe.estimator_.coef_,
index=X.columns[rfe.support_]).sort_values().plot(kind='barh')
from sklearn.feature_selection import RFE
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.pipeline import make_pipeline, make_union
from tpot.builtins import StackingEstimator
from xgboost import XGBClassifier
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE',
sep='COLUMN_SEPARATOR',
dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=42)
# Score on the training set was:0.86
exported_pipeline = make_pipeline(
StackingEstimator(estimator=XGBClassifier(learning_rate=0.1,
max_depth=3,
min_child_weight=16,
n_estimators=100,
nthread=1,
subsample=0.25)),
RFE(estimator=ExtraTreesClassifier(criterion="entropy",
max_features=0.8,
n_estimators=100),
step=0.7000000000000001), GaussianNB())
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)
def logitRegression(data):
# Feature Selection
logistic = LogisticRegression()
rfe = RFE(logistic, 18)
rfe = rfe.fit(inputs, winners)
print(rfe.support_)
print(rfe.ranking_)
features = rfe.support_
print("\nFeature index: " + str(np.where(features == True)))
# creating testing and training set
X_train, X_test, Y_train, Y_test = train_test_split(inputs,
winners,
test_size=0.33)
# train scikit learn model
clf = LogisticRegression()
clf.fit(X_train, Y_train)
score = round(clf.score(X_test, Y_test), 2)
print('score Scikit learn: ', score)
logistic.fit(inputs, winners)
predicted = logistic.predict(X_test)
print("Predicted: " + str(predicted))
plt.figure()
plt.plot(predicted)
# Metrics: confusion matrix
cm = metrics.confusion_matrix(Y_test, predicted)
print(cm)
# plot
plt.figure(figsize=(2, 2))
sns.heatmap(cm,
annot=True,
fmt=".3f",
linewidths=.5,
square=True,
cmap='Blues_r')
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
all_sample_title = 'Accuracy Score: {0}'.format(score)
plt.title(all_sample_title, size=15)
plt.show()
# cross validation
kfold = sklearn.cross_validation.KFold(X_train.shape[0], n_folds=10)
modelCV = LogisticRegression()
scoring = 'accuracy'
results = sklearn.metrics.accuracy_score(Y_test, predicted)
print("\n\n 10-fold cross validation average accuracy: %.3f" %
(results.mean()))
print("\n")
# precision
print(classification_report(Y_test, predicted))
# ROC
logit_roc_auc = roc_auc_score(Y_test, logistic.predict(X_test))
fpr, tpr, thresholds = roc_curve(Y_test,
logistic.predict_proba(X_test)[:, 1])
plt.figure()
plt.plot(fpr,
tpr,
label='Logistic Regression (area = %0.2f)' % logit_roc_auc)
plt.plot([0, 1], [0, 1], 'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.savefig('Log_ROC')
plt.show()
# train with selected features
train_cols = [
'Action 2', 'Action 9', 'Action 10', 'Action 11', 'Action 12',
'Action 13', 'Action 14', 'Action 16', 'Action 18', 'Action 24',
'Action 32', 'Action 41', 'Action 48', 'Action 53', 'Action 57',
'2gram 10', '3gram 2', '3gram 9'
]
X = data[train_cols]
#print(X)
y = data['Winner']
logit_model = sm.Logit(y.astype(float), X.astype(float))
result = logit_model.fit(method='bfgs')
print(result.summary())
# In[ ]:
from sklearn.linear_model import LogisticRegression
from sklearn.feature_selection import RFE
cols = [
"Age", "Fare", "TravelAlone", "Pclass_1", "Pclass_2", "Embarked_C",
"Embarked_S", "Sex_male", "IsMinor"
]
X = final_train[cols]
y = final_train['Survived']
# Build a logreg and compute the feature importances
model = LogisticRegression()
# create the RFE model and select 8 attributes
rfe = RFE(model, 8)
rfe = rfe.fit(X, y)
# summarize the selection of the attributes
print('Selected features: %s' % list(X.columns[rfe.support_]))
# <a id="t4.1.2."></a>
# ### 4.1.2. Feature ranking with recursive feature elimination and cross-validation
#
# RFECV performs RFE in a cross-validation loop to find the optimal number or the best number of features. Hereafter a recursive feature elimination applied on logistic regression with automatic tuning of the number of features selected with cross-validation.
# In[ ]:
from sklearn.feature_selection import RFECV
# Create the RFE object and compute a cross-validated score.
# The "accuracy" scoring is proportional to the number of correct classifications
rfecv = RFECV(estimator=LogisticRegression(),