def run(X_train,
y_train,
X_test,
y_test,
predciction_filename=None,
graph_name=None):
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
param_grid = {
'activation': ['identity', 'logistic', 'tanh'],
'alpha': [0.0001],
'batch_size': ['auto'],
'learning_rate_init': [0.001],
'max_iter': [2000], #Higher numbers will avoid ConvergenceWarnings
'hidden_layer_sizes': [(1, ), (2, ), (5, ), (2, 2), (3, 5)]
}
gs = GridSearchCV(MLPClassifier(),
param_grid,
cv=2,
n_jobs=-1,
scoring='accuracy')
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
if graph_name != None:
performance.plot_roc(gs, X_test, y_test, graph_name)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)
def run(X_train,
y_train,
X_test,
y_test,
predciction_filename=None,
graph_name=None):
# param_grid ={
# 'n_estimators':[10,20],
# 'max_depth':[2],
# 'criterion':['gini','entropy'],
# 'max_depth':[3,4,5,6]
# }
param_grid = {
'n_estimators': [10, 20, 50, 80],
'learning_rate': [1, .8, .6, .4],
}
gs = GridSearchCV(AdaBoostClassifier(),
param_grid,
cv=2,
n_jobs=-1,
scoring='accuracy')
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
if graph_name != None:
performance.plot_roc(gs, X_test, y_test, graph_name)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)
def run(X_train, y_train, X_test, y_test, predciction_filename=None):
if (len(X_train[0])) == 1:
eprint("\nERROR: MPP number of dimensions is equal to 1\n")
sys.exit()
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
param_grid = {
'case': [1, 2, 3],
}
gs = GridSearchCV(MPPClassifier(), param_grid, cv=4, n_jobs=1)
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)
def run(X_train,
y_train,
X_test,
y_test,
collapseType=-1,
predciction_filename=None,
graph_name=None):
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
param_grid = {
'criterion': ['gini', 'entropy'],
'max_depth': np.arange(2, 8)
}
gs = GridSearchCV(tree.DecisionTreeClassifier(),
param_grid,
cv=4,
n_jobs=-1,
scoring='accuracy')
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
classifier, accuracy, precision, recall, f1, confusion_matrix = performance.get_scores(
gs.best_params_, predicted_classes, y_test, predciction_filename)
#Save Deceision tree
if graph_name != None:
class_names = performance.get_class_labels(collapseType)
feature_names = [
'Age', 'Gender', 'Education', 'Country', 'Ethnicity',
'Neuroticism', 'Extraversion', 'Openness', 'Agreeableness',
'Conscientiousness', 'Impulsiveness', 'Sensation'
]
tree_data = tree.export_graphviz(gs.best_estimator_,
out_file=None,
feature_names=feature_names,
class_names=class_names,
filled=True,
rounded=True,
special_characters=True)
graph = graphviz.Source(tree_data)
graph.render(graph_name + "_DT")
#predciction_filename is not the rite naming scheme but it should work for these purposes
performance.plot_roc(gs, X_test, y_test, predciction_filename)
return classifier, accuracy, precision, recall, f1, confusion_matrix
def run(X_train,
y_train,
X_test,
y_test,
predciction_filename=None,
graph_name=None):
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
param_grid = {'n_neighbors': [5, 10, 20, 40], 'p': [1, 2, 3, np.inf]}
gs = GridSearchCV(KNeighborsClassifier(), param_grid, cv=4, n_jobs=-1)
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
if graph_name != None:
performance.plot_roc(gs, X_test, y_test, graph_name)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)
def run(X_train,
y_train,
X_test,
y_test,
predciction_filename=None,
graph_name=None):
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
param_grid = {
'C': [1, 2, 3, 4, 5, 6, 7],
'gamma': [0.001, 0.0001, 0.01, 0.1, 1, 10, 100],
'probability': [True]
}
gs = GridSearchCV(SVC(), param_grid, cv=2, n_jobs=-1, scoring='accuracy')
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
if graph_name != None:
performance.plot_roc(gs, X_test, y_test, graph_name)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)
def run(X_train, y_train, X_test, y_test, predciction_filename=None):
#Find the best parameters using GridSearchCV -- SPECIFY param_grid
#epsilon is only used for WTA
param_grid = [{
'algo': ['kMeans'],
'k_value': [6, 10],
'minkowski_p': [1, 2],
'max_iter': [20]
}, {
'algo': ['WTA'],
'epsilon': [.001],
'k_value': [12],
'minkowski_p': [1, 2],
'max_iter': [10]
}]
gs = GridSearchCV(clusteringClassifier(), param_grid, cv=2, n_jobs=-1)
gs.fit(X_train, y_train)
predicted_classes = gs.best_estimator_.predict(X_test)
return performance.get_scores(gs.best_params_, predicted_classes, y_test,
predciction_filename)