def test_cross_val_generator_mask_indices_same():
# Test that the cross validation generators return the same results when
# indices=True and when indices=False
y = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2])
labels = np.array([1, 1, 2, 3, 3, 3, 4])
loo_mask = cval.LeaveOneOut(5, indices=False)
loo_ind = cval.LeaveOneOut(5, indices=True)
lpo_mask = cval.LeavePOut(10, 2, indices=False)
lpo_ind = cval.LeavePOut(10, 2, indices=True)
kf_mask = cval.KFold(10, 5, indices=False, shuffle=True, random_state=1)
kf_ind = cval.KFold(10, 5, indices=True, shuffle=True, random_state=1)
skf_mask = cval.StratifiedKFold(y, 3, indices=False)
skf_ind = cval.StratifiedKFold(y, 3, indices=True)
lolo_mask = cval.LeaveOneLabelOut(labels, indices=False)
lolo_ind = cval.LeaveOneLabelOut(labels, indices=True)
lopo_mask = cval.LeavePLabelOut(labels, 2, indices=False)
lopo_ind = cval.LeavePLabelOut(labels, 2, indices=True)
ps_mask = cval.PredefinedSplit([1, 1, 2, 2], indices=False)
ps_ind = cval.PredefinedSplit([1, 1, 2, 2], indices=True)
for cv_mask, cv_ind in [(loo_mask, loo_ind), (lpo_mask, lpo_ind),
(kf_mask, kf_ind), (skf_mask, skf_ind),
(lolo_mask, lolo_ind), (lopo_mask, lopo_ind),
(ps_mask, ps_ind)]:
for (train_mask, test_mask), (train_ind, test_ind) in \
zip(cv_mask, cv_ind):
assert_array_equal(np.where(train_mask)[0], train_ind)
assert_array_equal(np.where(test_mask)[0], test_ind)
def train_gbr(X_input_train, Y_input_train, X_input_test, Y_input_test, name):
"""
Function to train a Gradient Boosting regression model with the Scikit Learn API
This functions trains and saves the network as a pickle file in ./silicat/saved/
INPUTS:
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
name: String
The name of the file for saving the network
OUTPUTS:
A saved network in ./silicat/saved/ with filename = name.
"""
# this is for the cross-validation stuff, we put the test data at the end and get their indexes
X_dataset = np.concatenate([X_input_train, X_input_test])
Y_dataset = np.concatenate([Y_input_train, Y_input_test])
#ttt = test[len(x_i_g):len(x_i_g)+len(x_t_g),:] /// (ttt==x_t_g).all() => I found this technic like that, playing around
test_idx = np.arange(len(X_input_train),
len(X_input_train) + len(X_input_test))
# and we setup the cross-validation here
ps = cross_validation.PredefinedSplit(test_fold=test_idx)
# now we perform the gridsearch and fit the model, get the best nmodel and save it using joblib
#mg = GridSearchCV(ensemble.GradientBoostingRegressor(), cv=ps,param_grid={"max_depth": [4,5,6],"learning_rate": [0.01,0.1,1.0,10.0]},n_jobs = 1)
# Fit regression model
params = {
'n_estimators': 1000,
'max_depth': 2,
'min_samples_split': 1,
'learning_rate': 0.1,
'loss': 'ls'
}
mg = ensemble.GradientBoostingRegressor(**params)
mg.fit(X_input_train, Y_input_train.ravel())
joblib.dump(
mg,
os.path.dirname(os.path.abspath(__file__)) + '/saved/' + name + '.pkl')
def test_predefinedsplit_with_kfold_split():
# Check that PredefinedSplit can reproduce a split generated by Kfold.
folds = -1 * np.ones(10)
kf_train = []
kf_test = []
for i, (train_ind, test_ind) in enumerate(cval.KFold(10, 5, shuffle=True)):
kf_train.append(train_ind)
kf_test.append(test_ind)
folds[test_ind] = i
ps_train = []
ps_test = []
ps = cval.PredefinedSplit(folds)
for train_ind, test_ind in ps:
ps_train.append(train_ind)
ps_test.append(test_ind)
assert_array_equal(ps_train, kf_train)
assert_array_equal(ps_test, kf_test)
def train_svm(X_input_train, Y_input_train, X_input_test, Y_input_test, name):
"""
Function to train a support vector machine model with the Scikit Learn API
This functions trains and saves the network as a pickle file in ./silicat/saved/
INPUTS:
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
X_input_train: Numpy array
The training input values
name: String
The name of the file for saving the network
OUTPUTS:
A saved network in ./silicat/saved/ with filename = name.
"""
# this is for the cross-validation stuff, we put the test data at the end and get their indexes
X_dataset = np.concatenate([X_input_train, X_input_test])
Y_dataset = np.concatenate([Y_input_train, Y_input_test])
#ttt = test[len(x_i_g):len(x_i_g)+len(x_t_g),:] /// (ttt==x_t_g).all() => I found this technic like that, playing around
test_idx = np.arange(len(X_input_train),
len(X_input_train) + len(X_input_test))
# and we setup the cross-validation here
ps = cross_validation.PredefinedSplit(test_fold=test_idx)
# now we perform the gridsearch and fit the model, get the best nmodel and save it using joblib
#mg = GridSearchCV(SVR(kernel='rbf',epsilon=0.1), cv=10,param_grid={"C":[0.01,0.1,1.0,10.0,100.0], "epsilon"=[0]},n_jobs = 1)
mg = SVR(kernel='rbf', C=1.5, epsilon=0.01)
mg.fit(X_input_train, Y_input_train.ravel())
joblib.dump(
mg,
os.path.dirname(os.path.abspath(__file__)) + '/saved/' + name + '.pkl')
def test_cross_val_generator_with_default_indices():
X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
y = np.array([1, 1, 2, 2])
labels = np.array([1, 2, 3, 4])
loo = cval.LeaveOneOut(4)
lpo = cval.LeavePOut(4, 2)
kf = cval.KFold(4, 2)
skf = cval.StratifiedKFold(y, 2)
lolo = cval.LeaveOneLabelOut(labels)
lopo = cval.LeavePLabelOut(labels, 2)
ss = cval.ShuffleSplit(2)
ps = cval.PredefinedSplit([1, 1, 2, 2])
for cv in [loo, lpo, kf, skf, lolo, lopo, ss, ps]:
for train, test in cv:
assert_not_equal(np.asarray(train).dtype.kind, 'b')
assert_not_equal(np.asarray(train).dtype.kind, 'b')
X[train], X[test]
y[train], y[test]
# try to keep n_estimators at 500 or less for performance reasons, over 2000 may exceed 8 GB ram
if do_optimize:
# cv_gs = cv.ShuffleSplit(len(train_y), n_iter=4, test_size=0.35)
# 4 folds without shuffling gives better cross validation scores
# cv_gs = cv.KFold(len(train_y), n_folds=4, shuffle=False)
# custom split based on predicting the first/last 5 days from the remaining of each month
split_arr = np.array(
[0, 0, 0, 0, 0, -1, -1, -1, -1, -1, -1, -1, -1, -1, 1, 1, 1, 1, 1])
train_split_f = lambda x: split_arr[x.index.day - 1]
train_split = train_set_df.apply(train_split_f)["atemp"].values
cv_gs = cv.PredefinedSplit(train_split)
regist_grid_search = sklearn.grid_search.GridSearchCV(
ens.BaggingRegressor(base_estimator=ens.AdaBoostRegressor(
base_estimator=tree.DecisionTreeRegressor())),
search_space_regist,
cv=cv_gs,
scoring="mean_squared_error",
refit=False,
n_jobs=2,
pre_dispatch="2*n_jobs",
verbose=3)
casual_grid_search = sklearn.grid_search.GridSearchCV(
ens.BaggingRegressor(base_estimator=ens.AdaBoostRegressor(
base_estimator=tree.DecisionTreeRegressor())),
"max_depth": [10],
"max_leaf_nodes": [None],
"n_estimators": [500]
}
# cv_gs = cv.ShuffleSplit(len(train_y), n_iter=4, test_size=0.35)
# 4 folds without shuffling gives better cross validation scores
# cv_gs = cv.KFold(len(train_y), n_folds=4, shuffle=False)
# custom split based on predicting the first/last 5 days from the remaining of each month
split_arr = np.array(
[0, 0, 0, 0, 0, -1, -1, -1, -1, -1, -1, -1, -1, -1, 1, 1, 1, 1, 1])
split_f = lambda x: split_arr[x.index.day - 1]
test_split = train_set_df.apply(split_f)["atemp"].values
cv_gs = cv.PredefinedSplit(test_split)
# split_f = lambda x: (x.index.day - 1)// 15
grid_search_gs = sklearn.grid_search.GridSearchCV(
ens.RandomForestRegressor(),
search_space,
cv=cv_gs,
scoring="mean_squared_error",
refit=False,
n_jobs=1,
pre_dispatch="2*n_jobs",
verbose=3)
print("running grid search")
grid_search_gs.fit(train_X, train_y)
# Convert 'Day' to 'datetime' and set as index
hires.Day = pd.to_datetime(hires.Day, unit='D')
hires.set_index('Day', inplace=True)
# Extract first column (daily hires) and convert to 'float'
hires = hires.iloc[:,0].astype('float').to_frame('Hires')
# Apply logarithmic transformation
# Create 7 new variables representing the lagged time series at lag = 1, ..., 7
# Create 2 new variables representing the smoothed time series
# (rolling averages at 7 and 30 days)
# Drop missing values
# Define cross-validation split by leaving out 2016 as test set
split = cv.PredefinedSplit(test_fold=(hires.index.year == 2016) - 1)
# Create a pipeline that scales the data and trains a support vector regression
# model
# Fit the model
# Compute MSE for split
# Determine ‘optimal’ kernel and value of C by cross-validation
# Plot original time series and prediction from January 2015 onwards
