def simple_naive_bayes(X, y): n, _ = X.shape nTrain = int(0.5*n) #training on 50% of the data Xtrain = X[:nTrain,:] ytrain = y[:nTrain] Xtest = X[nTrain:,:] ytest = y[nTrain:] clf = MultinomialNB().fit(Xtrain, ytrain) predict_y = clf.predict(Xtest) print ytest print predict_y print rmsle(ytest, predict_y)
def simple_naive_bayes(X, y):
n, _ = X.shape
nTrain = int(0.5 * n) #training on 50% of the data
Xtrain = X[:nTrain, :]
ytrain = y[:nTrain]
Xtest = X[nTrain:, :]
ytest = y[nTrain:]
clf = MultinomialNB().fit(Xtrain, ytrain)
predict_y = clf.predict(Xtest)
print ytest
print predict_y
print rmsle(ytest, predict_y)
def logistic_regression(X, y):
n, _ = X.shape
nTrain = int(0.5 * n) #training on 50% of the data
Xtrain = X[:nTrain, :]
ytrain = y[:nTrain]
Xtest = X[nTrain:, :]
ytest = y[nTrain:]
for i, C in enumerate(10.**np.arange(1, 6)):
clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01)
clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01)
clf_l1_LR.fit(Xtrain, ytrain)
clf_l2_LR.fit(Xtrain, ytrain)
y1 = clf_l1_LR.predict(Xtest)
y2 = clf_l2_LR.predict(Xtest)
#L1 penalty
print "L1 Penalty with C=" + str(C)
print rmsle(ytest, y1)
print "L2 Penalty with C=" + str(C)
#L2 penalty
print rmsle(ytest, y2)
logreg = LinearRegression()
logreg.fit(Xtrain, ytrain)
y3 = logreg.predict(Xtest)
print "Linear Regression"
print y3
print rmsle(ytest, y3)
def logistic_regression(X, y):
n, _ = X.shape
nTrain = int(0.5*n) #training on 50% of the data
Xtrain = X[:nTrain,:]
ytrain = y[:nTrain]
Xtest = X[nTrain:,:]
ytest = y[nTrain:]
for i, C in enumerate(10. ** np.arange(1, 6)):
clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01)
clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01)
clf_l1_LR.fit(Xtrain, ytrain)
clf_l2_LR.fit(Xtrain, ytrain)
y1 = clf_l1_LR.predict(Xtest)
y2 = clf_l2_LR.predict(Xtest)
#L1 penalty
print "L1 Penalty with C=" + str(C)
print rmsle(ytest, y1)
print "L2 Penalty with C=" + str(C)
#L2 penalty
print rmsle(ytest, y2)
logreg = LinearRegression()
logreg.fit(Xtrain, ytrain)
y3 = logreg.predict(Xtest)
print "Linear Regression"
print y3
print rmsle(ytest,y3)
Xtrain = X[:nTrain,:]
y_casual_train = y_casual[:nTrain]
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:,:]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
#clf = SVC(kernel='poly')
#clf.fit(Xtrain,ytrain)
#pred = clf.predict(Xtest)
#print "best estimator = ",clf.best_estimator_
#print "RMSE poly = ", rmsle(ytest, pred)
#new stuff
clf_regis = SVR(kernel='poly')
clf_regis.fit(Xtrain,y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = SVR(kernel='poly')
clf_casual.fit(Xtrain,y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE poly total = ", rmsle(y_total_test, pred_total)
def decision_tree(X, y1, y2, y3):
n, _ = X.shape
nTrain = int(0.5 * n) #training on 50% of the data
Xtrain = X[:nTrain, :]
ytrain = y1[:nTrain]
ytrain_registered = y2[:nTrain]
ytest_registered = y2[nTrain:]
ytrain_casual = y3[:nTrain]
ytest_casual = y3[nTrain:]
Xtest = X[nTrain:, :]
ytest = y1[nTrain:]
#regular
clf_1 = DecisionTreeRegressor(max_depth=None)
clf_2 = AdaBoostRegressor(DecisionTreeRegressor(max_depth=None),
n_estimators=500)
clf_4 = RandomForestRegressor(n_estimators=500,
max_depth=None,
min_samples_split=1,
random_state=0)
clf_5 = ExtraTreesRegressor(n_estimators=500,
max_depth=None,
min_samples_split=1,
random_state=0)
clf_3 = GradientBoostingRegressor(n_estimators=500,
max_depth=None,
random_state=0)
print "finished generating tree"
clf_1.fit(Xtrain, ytrain_registered)
clf_2.fit(Xtrain, ytrain_registered)
clf_3.fit(Xtrain, ytrain_registered)
clf_4.fit(Xtrain, ytrain_registered)
clf_5.fit(Xtrain, ytrain_registered)
print 'Finished fitting'
dt_regular = clf_1.predict(Xtest)
ada_regular = clf_2.predict(Xtest)
grad_regular = clf_3.predict(Xtest)
rf_regular = clf_4.predict(Xtest)
et_regular = clf_5.predict(Xtest)
#casual
print "finished generating tree"
clf_1.fit(Xtrain, ytrain_casual)
clf_2.fit(Xtrain, ytrain_casual)
clf_3.fit(Xtrain, ytrain_casual)
clf_4.fit(Xtrain, ytrain_casual)
clf_5.fit(Xtrain, ytrain_casual)
print 'Finished fitting'
dt_casual = clf_1.predict(Xtest)
ada_casual = clf_2.predict(Xtest)
grad_casual = clf_3.predict(Xtest)
rf_casual = clf_4.predict(Xtest)
et_casual = clf_5.predict(Xtest)
feature_imps = clf_4.feature_importances_
print "regular decision tree"
print rmsle(ytest, dt_regular + dt_casual)
print "boosted decision tree"
print rmsle(ytest, ada_regular + ada_casual)
print "gradient tree boosting"
print rmsle(ytest, grad_regular + grad_casual)
print "random forest classifier"
print rmsle(ytest, rf_regular + rf_casual)
print "extra trees classifier"
print rmsle(ytest, et_casual + et_regular)
print "feature importances"
print feature_imps
Xtest = X[nTrain:,:]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
clf_regis = SVR(kernel='linear')
clf_regis.fit(Xtrain,y_regis_train)
pred_regis = clf_regis.predict(Xtest)
#print "best estimator = ",clf.best_estimator_
#print "RMSLE linear registered = ", rmsle(y_regis_test, pred_regis)
clf_casual = SVR(kernel='linear')
clf_casual.fit(Xtrain,y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print len(y_total_test)
print len(pred_total)
# if y_total is None:
# print "y is none"
# if pred_total is None:
# print "pred is None"
print "RMSLE linear total = ", rmsle(y_total_test, pred_total)
#np.random.seed(42)
#np.random.shuffle(idx)
#X = X[idx]
#y = y[idx]
Xtrain = X[:nTrain,:]
y_casual_train = y_casual[:nTrain]
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:,:]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
neighbors = 4
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
clf_regis = KNeighborsRegressor(n_neighbors=neighbors,algorithm='kd_tree',leaf_size=70,p=1)
clf_regis.fit(Xtrain,y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = KNeighborsRegressor(n_neighbors=neighbors,algorithm='kd_tree',leaf_size=70,p=1)
clf_casual.fit(Xtrain,y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE sigmoid total = ", rmsle(y_total_test, pred_total)
def decision_tree(X, y1, y2, y3):
n, _ = X.shape
nTrain = int(0.5 * n) #training on 50% of the data
Xtrain = X[:nTrain, :]
ytrain = y1[:nTrain]
ytrain_registered = y2[:nTrain]
ytest_registered = y2[nTrain:]
ytrain_casual = y3[:nTrain]
ytest_casual = y3[nTrain:]
Xtest = X[nTrain:, :]
ytest = y1[nTrain:]
#regular
#clf_1 = DecisionTreeRegressor(max_depth=None)
#clf_2 = AdaBoostRegressor(DecisionTreeRegressor(max_depth=None),
#n_estimators=500)
clf_4 = RandomForestRegressor(bootstrap=True,
compute_importances=None,
criterion='mse',
max_depth=None,
max_features='auto',
min_density=None,
min_samples_leaf=2,
min_samples_split=2,
n_estimators=2000,
n_jobs=1,
oob_score=True,
random_state=None,
verbose=0)
#clf_5 = ExtraTreesRegressor(n_estimators=500, max_depth=None,
#min_samples_split=1, random_state=0)
#clf_3 = GradientBoostingRegressor(n_estimators=500,
#max_depth=None, random_state=0)
#rmsele_scorer = make_scorer(rmsle, greater_is_better=False)
#tuned_parameters = [{'max_features': ['sqrt', 'log2', 'auto'], 'max_depth': [5, 8, 12], 'min_samples_leaf': [2, 5, 10]}]
# rf_registered = GridSearchCV(RandomForestRegressor(n_jobs=1, n_estimators=1000), tuned_parameters, cv=3, verbose=2, scoring=rmsele_scorer).fit(Xtrain, ytrain_registered)
# rf_casual = GridSearchCV(RandomForestRegressor(n_jobs=1, n_estimators=1000), tuned_parameters, cv=3, verbose=2, scoring=rmsele_scorer).fit(Xtrain, ytrain_casual)
print "Best parameters"
# print rf_registered.best_estimator_
# print rf_casual.best_estimator_
clf_4.fit(Xtrain, ytrain)
rf_total = clf_4.predict(Xtest)
rf_ytrain = clf_4.predict(Xtrain)
print "finished generating regressor"
#clf_1.fit(Xtrain, ytrain_registered)
#clf_2.fit(Xtrain, ytrain_registered)
#clf_3.fit(Xtrain, ytrain_registered)
clf_4.fit(Xtrain, ytrain_registered)
#clf_5.fit(Xtrain, ytrain_registered)
print 'Finished fitting'
#dt_regular = clf_1.predict(Xtest)
#ada_regular = clf_2.predict(Xtest)
#grad_regular = clf_3.predict(Xtest)
rf_regular = clf_4.predict(Xtest)
#et_regular = clf_5.predict(Xtest)
#casual
print "finished generating tree"
#clf_1.fit(Xtrain, ytrain_casual)
#clf_2.fit(Xtrain, ytrain_casual)
#clf_3.fit(Xtrain, ytrain_casual)
clf_4.fit(Xtrain, ytrain_casual)
#clf_5.fit(Xtrain, ytrain_casual)
print 'Finished fitting'
#dt_casual = clf_1.predict(Xtest)
#ada_casual = clf_2.predict(Xtest)
#grad_casual = clf_3.predict(Xtest)
rf_casual = clf_4.predict(Xtest)
# #et_casual = clf_5.predict(Xtest)
# feature_imps = clf_4.feature_importances_
# print "regular decision tree"
# print rmsle(ytest, dt_regular + dt_casual)
# print "boosted decision tree"
# print rmsle(ytest, ada_regular + ada_casual)
# print "gradient tree boosting"
# print rmsle(ytest, grad_regular + grad_casual)
print "random forest classifier"
print rmsle(ytest, rf_regular + rf_casual)
print rmsle(ytest, rf_total)
print rmsle(ytrain, rf_ytrain)
# print "extra trees classifier"
# print rmsle(ytest, et_casual + et_regular)
print "feature importances"
y_casual_train = y_casual[:nTrain]
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:, :]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
'''
#rbf
param_grid = {'C': [1, 5, 10, 100],'gamma': [0.00001,0.0001, 0.001, 0.01, 0.1],}
#clf = GridSearchCV(SVC(kernel='rbf'), param_grid,n_jobs=-1)
clf = SVC(kernel='rbf',C=5.0,gamma=0.0001)
clf.fit(Xtrain,ytrain)
pred = clf.predict(Xtest)
print "best estimator = ",clf.best_estimator_
print "RMSE rbf = ", rmsle(ytest, pred)
#print classification_report(ytest, pred)
'''
#new stuff
clf_regis = SVR(kernel='rbf')
clf_regis.fit(Xtrain, y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = SVR(kernel='rbf')
clf_casual.fit(Xtrain, y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE rbf total = ", rmsle(y_total_test, pred_total)
def decision_tree(X, y1, y2, y3):
n, _ = X.shape
nTrain = int(0.5*n) #training on 50% of the data
Xtrain = X[:nTrain,:]
ytrain = y1[:nTrain]
ytrain_registered = y2[:nTrain]
ytest_registered = y2[nTrain:]
ytrain_casual = y3[:nTrain]
ytest_casual = y3[nTrain:]
Xtest = X[nTrain:,:]
ytest = y1[nTrain:]
#regular
#clf_1 = DecisionTreeRegressor(max_depth=None)
#clf_2 = AdaBoostRegressor(DecisionTreeRegressor(max_depth=None),
#n_estimators=500)
clf_4 = RandomForestRegressor(bootstrap=True, compute_importances=None,
criterion='mse', max_depth=None, max_features='auto',
min_density=None, min_samples_leaf=2, min_samples_split=2,
n_estimators=2000, n_jobs=1, oob_score=True, random_state=None,
verbose=0)
#clf_5 = ExtraTreesRegressor(n_estimators=500, max_depth=None,
#min_samples_split=1, random_state=0)
#clf_3 = GradientBoostingRegressor(n_estimators=500,
#max_depth=None, random_state=0)
#rmsele_scorer = make_scorer(rmsle, greater_is_better=False)
#tuned_parameters = [{'max_features': ['sqrt', 'log2', 'auto'], 'max_depth': [5, 8, 12], 'min_samples_leaf': [2, 5, 10]}]
# rf_registered = GridSearchCV(RandomForestRegressor(n_jobs=1, n_estimators=1000), tuned_parameters, cv=3, verbose=2, scoring=rmsele_scorer).fit(Xtrain, ytrain_registered)
# rf_casual = GridSearchCV(RandomForestRegressor(n_jobs=1, n_estimators=1000), tuned_parameters, cv=3, verbose=2, scoring=rmsele_scorer).fit(Xtrain, ytrain_casual)
print "Best parameters"
# print rf_registered.best_estimator_
# print rf_casual.best_estimator_
clf_4.fit(Xtrain, ytrain)
rf_total = clf_4.predict(Xtest)
rf_ytrain = clf_4.predict(Xtrain)
print "finished generating regressor"
#clf_1.fit(Xtrain, ytrain_registered)
#clf_2.fit(Xtrain, ytrain_registered)
#clf_3.fit(Xtrain, ytrain_registered)
clf_4.fit(Xtrain, ytrain_registered)
#clf_5.fit(Xtrain, ytrain_registered)
print 'Finished fitting'
#dt_regular = clf_1.predict(Xtest)
#ada_regular = clf_2.predict(Xtest)
#grad_regular = clf_3.predict(Xtest)
rf_regular = clf_4.predict(Xtest)
#et_regular = clf_5.predict(Xtest)
#casual
print "finished generating tree"
#clf_1.fit(Xtrain, ytrain_casual)
#clf_2.fit(Xtrain, ytrain_casual)
#clf_3.fit(Xtrain, ytrain_casual)
clf_4.fit(Xtrain, ytrain_casual)
#clf_5.fit(Xtrain, ytrain_casual)
print 'Finished fitting'
#dt_casual = clf_1.predict(Xtest)
#ada_casual = clf_2.predict(Xtest)
#grad_casual = clf_3.predict(Xtest)
rf_casual = clf_4.predict(Xtest)
# #et_casual = clf_5.predict(Xtest)
# feature_imps = clf_4.feature_importances_
# print "regular decision tree"
# print rmsle(ytest, dt_regular + dt_casual)
# print "boosted decision tree"
# print rmsle(ytest, ada_regular + ada_casual)
# print "gradient tree boosting"
# print rmsle(ytest, grad_regular + grad_casual)
print "random forest classifier"
print rmsle(ytest, rf_regular + rf_casual)
print rmsle(ytest, rf_total)
print rmsle(ytrain, rf_ytrain)
# print "extra trees classifier"
# print rmsle(ytest, et_casual + et_regular)
print "feature importances"
Xtrain = X[:nTrain, :]
y_casual_train = y_casual[:nTrain]
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:, :]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
#clf = SVC(kernel='poly')
#clf.fit(Xtrain,ytrain)
#pred = clf.predict(Xtest)
#print "best estimator = ",clf.best_estimator_
#print "RMSE poly = ", rmsle(ytest, pred)
#new stuff
clf_regis = SVR(kernel='poly')
clf_regis.fit(Xtrain, y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = SVR(kernel='poly')
clf_casual.fit(Xtrain, y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE poly total = ", rmsle(y_total_test, pred_total)
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:,:]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
'''
#rbf
param_grid = {'C': [1, 5, 10, 100],'gamma': [0.00001,0.0001, 0.001, 0.01, 0.1],}
#clf = GridSearchCV(SVC(kernel='rbf'), param_grid,n_jobs=-1)
clf = SVC(kernel='rbf',C=5.0,gamma=0.0001)
clf.fit(Xtrain,ytrain)
pred = clf.predict(Xtest)
print "best estimator = ",clf.best_estimator_
print "RMSE rbf = ", rmsle(ytest, pred)
#print classification_report(ytest, pred)
'''
#new stuff
clf_regis = SVR(kernel='rbf')
clf_regis.fit(Xtrain,y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = SVR(kernel='rbf')
clf_casual.fit(Xtrain,y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE rbf total = ", rmsle(y_total_test, pred_total)
Xtrain = X[:nTrain, :]
y_casual_train = y_casual[:nTrain]
y_regis_train = y_regis[:nTrain]
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:, :]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
neighbors = 4
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
clf_regis = KNeighborsRegressor(n_neighbors=neighbors,
algorithm='kd_tree',
leaf_size=70,
p=1)
clf_regis.fit(Xtrain, y_regis_train)
pred_regis = clf_regis.predict(Xtest)
clf_casual = KNeighborsRegressor(n_neighbors=neighbors,
algorithm='kd_tree',
leaf_size=70,
p=1)
clf_casual.fit(Xtrain, y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print "RMSLE sigmoid total = ", rmsle(y_total_test, pred_total)
y_total_train = y_total[:nTrain]
Xtest = X[nTrain:, :]
y_casual_test = y_casual[nTrain:]
y_regis_test = y_regis[nTrain:]
y_total_test = y_total[nTrain:]
#linear
#param_grid = {'C': [1, 5, 10, 100],}
#clf = GridSearchCV(SVC(kernel='linear'), param_grid,n_jobs=-1)
clf_regis = SVR(kernel='linear')
clf_regis.fit(Xtrain, y_regis_train)
pred_regis = clf_regis.predict(Xtest)
#print "best estimator = ",clf.best_estimator_
#print "RMSLE linear registered = ", rmsle(y_regis_test, pred_regis)
clf_casual = SVR(kernel='linear')
clf_casual.fit(Xtrain, y_casual_train)
pred_casual = clf_casual.predict(Xtest)
pred_total = pred_casual + pred_regis
print len(y_total_test)
print len(pred_total)
# if y_total is None:
# print "y is none"
# if pred_total is None:
# print "pred is None"
print "RMSLE linear total = ", rmsle(y_total_test, pred_total)
def decision_tree(X, y1, y2, y3):
n, _ = X.shape
nTrain = int(0.5*n) #training on 50% of the data
Xtrain = X[:nTrain,:]
ytrain = y1[:nTrain]
ytrain_registered = y2[:nTrain]
ytest_registered = y2[nTrain:]
ytrain_casual = y3[:nTrain]
ytest_casual = y3[nTrain:]
Xtest = X[nTrain:,:]
ytest = y1[nTrain:]
#regular
clf_1 = DecisionTreeRegressor(max_depth=None)
clf_2 = AdaBoostRegressor(DecisionTreeRegressor(max_depth=None),
n_estimators=500)
clf_4 = RandomForestRegressor(n_estimators=500, max_depth=None,
min_samples_split=1, random_state=0)
clf_5 = ExtraTreesRegressor(n_estimators=500, max_depth=None,
min_samples_split=1, random_state=0)
clf_3 = GradientBoostingRegressor(n_estimators=500,
max_depth=None, random_state=0)
print "finished generating tree"
clf_1.fit(Xtrain, ytrain_registered)
clf_2.fit(Xtrain, ytrain_registered)
clf_3.fit(Xtrain, ytrain_registered)
clf_4.fit(Xtrain, ytrain_registered)
clf_5.fit(Xtrain, ytrain_registered)
print 'Finished fitting'
dt_regular = clf_1.predict(Xtest)
ada_regular = clf_2.predict(Xtest)
grad_regular = clf_3.predict(Xtest)
rf_regular = clf_4.predict(Xtest)
et_regular = clf_5.predict(Xtest)
#casual
print "finished generating tree"
clf_1.fit(Xtrain, ytrain_casual)
clf_2.fit(Xtrain, ytrain_casual)
clf_3.fit(Xtrain, ytrain_casual)
clf_4.fit(Xtrain, ytrain_casual)
clf_5.fit(Xtrain, ytrain_casual)
print 'Finished fitting'
dt_casual = clf_1.predict(Xtest)
ada_casual = clf_2.predict(Xtest)
grad_casual = clf_3.predict(Xtest)
rf_casual = clf_4.predict(Xtest)
et_casual = clf_5.predict(Xtest)
feature_imps = clf_4.feature_importances_
print "regular decision tree"
print rmsle(ytest, dt_regular + dt_casual)
print "boosted decision tree"
print rmsle(ytest, ada_regular + ada_casual)
print "gradient tree boosting"
print rmsle(ytest, grad_regular + grad_casual)
print "random forest classifier"
print rmsle(ytest, rf_regular + rf_casual)
print "extra trees classifier"
print rmsle(ytest, et_casual + et_regular)
print "feature importances"
print feature_imps
#np.random.seed(42) #np.random.shuffle(idx) #y = y[idx] #X = X[idx] # split the data Xtrain = X[:nTrain,:] ytrain = y[:nTrain] Xtest = X[nTrain:,:] ytest = y[nTrain:] #linear clf = SVC(kernel='linear') clf.fit(Xtrain,ytrain) pred = clf.predict(Xtest) print "RMSE linear = ", rmsle(ytest, pred) #polynomial clf = SVC(kernel='poly') clf.fit(Xtrain,ytrain) pred = clf.predict(Xtest) print "RMSE poly = ", rmsle(ytest, pred) #rbf clf = SVC(kernel='rbf') clf.fit(Xtrain,ytrain) pred = clf.predict(Xtest) print "RMSE rbf = ", rmsle(ytest, pred) #sigmoid clf = SVC(kernel='sigmoid')