def test_eval_measures():
#mainly regression tests
x = np.arange(20).reshape(4,5)
y = np.ones((4,5))
assert_equal(iqr(x, y), 5*np.ones(5))
assert_equal(iqr(x, y, axis=1), 2*np.ones(4))
assert_equal(iqr(x, y, axis=None), 9)
assert_equal(mse(x, y),
np.array([ 73.5, 87.5, 103.5, 121.5, 141.5]))
assert_equal(mse(x, y, axis=1),
np.array([ 3., 38., 123., 258.]))
assert_almost_equal(rmse(x, y),
np.array([ 8.5732141 , 9.35414347, 10.17349497,
11.02270384, 11.89537725]))
assert_almost_equal(rmse(x, y, axis=1),
np.array([ 1.73205081, 6.164414,
11.09053651, 16.0623784 ]))
assert_equal(maxabs(x, y),
np.array([ 14., 15., 16., 17., 18.]))
assert_equal(maxabs(x, y, axis=1),
np.array([ 3., 8., 13., 18.]))
assert_equal(meanabs(x, y),
np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))
assert_equal(meanabs(x, y, axis=1),
np.array([ 1.4, 6. , 11. , 16. ]))
assert_equal(meanabs(x, y, axis=0),
np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(bias(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(bias(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(medianbias(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianbias(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(vare(x, y),
np.array([ 31.25, 31.25, 31.25, 31.25, 31.25]))
assert_equal(vare(x, y, axis=1),
np.array([ 2., 2., 2., 2.]))
def test_eval_measures():
#mainly regression tests
x = np.arange(20).reshape(4,5)
y = np.ones((4,5))
assert_equal(iqr(x, y), 5*np.ones(5))
assert_equal(iqr(x, y, axis=1), 2*np.ones(4))
assert_equal(iqr(x, y, axis=None), 9)
assert_equal(mse(x, y),
np.array([ 73.5, 87.5, 103.5, 121.5, 141.5]))
assert_equal(mse(x, y, axis=1),
np.array([ 3., 38., 123., 258.]))
assert_almost_equal(rmse(x, y),
np.array([ 8.5732141 , 9.35414347, 10.17349497,
11.02270384, 11.89537725]))
assert_almost_equal(rmse(x, y, axis=1),
np.array([ 1.73205081, 6.164414,
11.09053651, 16.0623784 ]))
assert_equal(maxabs(x, y),
np.array([ 14., 15., 16., 17., 18.]))
assert_equal(maxabs(x, y, axis=1),
np.array([ 3., 8., 13., 18.]))
assert_equal(meanabs(x, y),
np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))
assert_equal(meanabs(x, y, axis=1),
np.array([ 1.4, 6. , 11. , 16. ]))
assert_equal(meanabs(x, y, axis=0),
np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(bias(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(bias(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(medianbias(x, y),
np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianbias(x, y, axis=1),
np.array([ 1., 6., 11., 16.]))
assert_equal(vare(x, y),
np.array([ 31.25, 31.25, 31.25, 31.25, 31.25]))
assert_equal(vare(x, y, axis=1),
np.array([ 2., 2., 2., 2.]))
def test_eval_measures():
# mainly regression tests
x = np.arange(20).reshape(4, 5)
y = np.ones((4, 5))
assert_equal(iqr(x, y), 5 * np.ones(5))
assert_equal(iqr(x, y, axis=1), 2 * np.ones(4))
assert_equal(iqr(x, y, axis=None), 9)
assert_equal(mse(x, y), np.array([73.5, 87.5, 103.5, 121.5, 141.5]))
assert_equal(mse(x, y, axis=1), np.array([3.0, 38.0, 123.0, 258.0]))
assert_almost_equal(
rmse(x, y),
np.array(
[8.5732141, 9.35414347, 10.17349497, 11.02270384, 11.89537725]
),
)
assert_almost_equal(
rmse(x, y, axis=1),
np.array([1.73205081, 6.164414, 11.09053651, 16.0623784]),
)
err = x - y
loc = np.where(x != 0)
err[loc] /= x[loc]
err[np.where(x == 0)] = np.nan
expected = np.sqrt(np.nanmean(err ** 2, 0) * 100)
assert_almost_equal(rmspe(x, y), expected)
err[np.where(np.isnan(err))] = 0.0
expected = np.sqrt(np.nanmean(err ** 2, 0) * 100)
assert_almost_equal(rmspe(x, y, zeros=0), expected)
assert_equal(maxabs(x, y), np.array([14.0, 15.0, 16.0, 17.0, 18.0]))
assert_equal(maxabs(x, y, axis=1), np.array([3.0, 8.0, 13.0, 18.0]))
assert_equal(meanabs(x, y), np.array([7.0, 7.5, 8.5, 9.5, 10.5]))
assert_equal(meanabs(x, y, axis=1), np.array([1.4, 6.0, 11.0, 16.0]))
assert_equal(meanabs(x, y, axis=0), np.array([7.0, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y), np.array([6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianabs(x, y, axis=1), np.array([1.0, 6.0, 11.0, 16.0]))
assert_equal(bias(x, y), np.array([6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(bias(x, y, axis=1), np.array([1.0, 6.0, 11.0, 16.0]))
assert_equal(medianbias(x, y), np.array([6.5, 7.5, 8.5, 9.5, 10.5]))
assert_equal(medianbias(x, y, axis=1), np.array([1.0, 6.0, 11.0, 16.0]))
assert_equal(vare(x, y), np.array([31.25, 31.25, 31.25, 31.25, 31.25]))
assert_equal(vare(x, y, axis=1), np.array([2.0, 2.0, 2.0, 2.0]))
def get_best_model(train, test, model_formula):
# Step 1: specify the form of the model
grid = 10**np.arange(-8, -3, dtype=np.float64)
best_alpha = []
best_score = 1000
# Step 2: Find the best hyper parameter, alpha
for alpha in grid:
model = smf.glm(formula=model_formula,
data=train,
family=sm.families.NegativeBinomial(alpha=alpha))
results = model.fit()
predictions = results.predict(test).astype(int)
score = eval_measures.meanabs(predictions, test.total_cases)
if score < best_score:
best_alpha = alpha
best_score = score
print('best alpha = ', best_alpha)
print('best score = ', best_score)
# Step 3: refit on entire dataset
full_dataset = pd.concat([train, test])
model = smf.glm(formula=model_formula,
data=full_dataset,
family=sm.families.NegativeBinomial(alpha=best_alpha))
fitted_model = model.fit()
return fitted_model
def negative_binomial_model_eval(self, x_train, x_test, y_train, y_test):
train = x_train.copy()
test = x_test.copy()
train['total_cases'] = y_train
test['total_cases'] = y_test
# Step 1: specify the form of the model
model_formula = train.columns[0]
for i in range(1, len(train.columns)-1):
model_formula = model_formula+" + "+train.columns[i]
model_formula = train.columns[-1] + ' ~ ' + model_formula
grid = 10 ** np.arange(-8, -3, dtype=np.float64)
best_alpha = []
best_score = 1000
# Step 2: Find the best hyper parameter, alpha
for alpha in grid:
model = smf.glm(formula=model_formula, data=train, family=sm.families.NegativeBinomial(alpha=alpha))
results = model.fit()
predictions = results.predict(test).astype(int)
score = eval_measures.meanabs(predictions, test.total_cases)
if score < best_score:
best_alpha = alpha
best_score = score
# st.write('best alpha = ', best_alpha)
# st.write('best score = ', best_score)
return best_alpha
def get_best_model(train, test):
# Step 1: specify the form of the model
model_formula = "total_cases ~ 1 + " "reanalysis_specific_humidity_g_per_kg + " "reanalysis_dew_point_temp_k + " "reanalysis_min_air_temp_k + " "station_min_temp_c + " "station_max_temp_c + " "station_avg_temp_c + " "reanalysis_air_temp_k"
grid = 10 ** np.arange(-8, -3, dtype=np.float64)
best_alpha = []
best_score = 1000
# Step 2: Find the best hyper parameter, alpha
for alpha in grid:
model = smf.glm(formula=model_formula,
data=train,
family=sm.families.NegativeBinomial(alpha=alpha))
results = model.fit()
predictions = results.predict(test).astype(int)
score = eval_measures.meanabs(predictions, test.total_cases)
if score < best_score:
best_alpha = alpha
best_score = score
print('Alpha = ', best_alpha)
print('Score = ', best_score)
# Step 3: refit on entire dataset
full_dataset = pd.concat([train, test])
model = smf.glm(formula=model_formula,
data=full_dataset,
family=sm.families.NegativeBinomial(alpha=best_alpha))
fitted_model = model.fit()
return fitted_model
def bestrandfrorest(train, test):
n_estimate = np.arange(2, 100, 2, dtype=np.float64)
rand_state = np.arange(2, 100, 2, dtype=np.float64)
best_estimate = []
best_rand_state = []
best_score = 1000
eee = 10 ** -6
train_X = train.copy()
train_Y = train_X.total_cases
train_X.drop('total_cases', axis=1, inplace=True)
train_X.drop('city', axis=1, inplace=True)
train_X.drop('week_start_date', axis=1, inplace=True)
test_X = test.copy()
test_Y = test_X.total_cases
test_X.drop('total_cases', axis=1, inplace=True)
test_X.drop('city', axis=1, inplace=True)
test_X.drop('week_start_date', axis=1, inplace=True)
for n in n_estimate:
for r in rand_state:
nest = int(n)
rnd = int(r)
randForestModel = RandomForestRegressor(n_estimators=nest, random_state=rnd)
randForestModel.fit(train_X, train_Y)
predictions = randForestModel.predict(test_X).astype(int)
acc = eval_measures.meanabs(predictions, test_Y)
if acc < best_score + eee:
best_score = acc
best_estimate = nest
best_rand_state = rnd
print(n)
print(best_estimate)
print(best_rand_state)
randForestModel = RandomForestRegressor(n_estimators=best_estimate, random_state=best_rand_state)
randForestModel.fit(train_X, train_Y)
predictions = randForestModel.predict(test_X).astype(int)
acc = eval_measures.meanabs(predictions, test_Y)
return randForestModel, acc
def printErrors(test, pred, model):
'''
Objective: to print errors of the models
Inputs:
test: test dataframe
pred: predictions
model: model that is used
Outputs:
Mean absolute error, mean squared error, root mean squared error
'''
print('MAE of ' + model + ': {:.4}'.format(meanabs(test, pred, axis=0)))
print('MSE of ' + model + ': {:.4}'.format(mse(test, pred, axis=0)))
print('RMSE of ' + model + ': {:.4}'.format(rmse(test, pred, axis=0)))
def train_negative_binomial_model(self, x_train, y_train, test_size):
'''generate and train the negative binomial model
:param xtrain: matrix with the features, pandas or numpy
:param ytrain: array with the targets, pandas or numpy
:param test_size: from 0 to 1, percentual of train to use as test in the parameter evaluatio of the model
:return: negative binomial model fitted
'''
x_train_train, x_train_test, y_train_train, y_train_test = train_test_split(
x_train, y_train, shuffle=False, test_size=test_size)
train = x_train_train.copy()
test = x_train_test.copy()
train['target'] = y_train_train
test['target'] = y_train_test
# Step 1: specify the form of the model
model_formula = train.columns[0]
for i in range(1, len(train.columns) - 1):
model_formula = model_formula + " + " + train.columns[i]
model_formula = train.columns[-1] + ' ~ ' + model_formula
grid = 10**np.arange(-8, -3, dtype=np.float64)
best_alpha = []
best_score = 1000
# Step 2: Find the best hyper parameter, alpha
for alpha in grid:
model = smf.glm(formula=model_formula,
data=train,
family=sm.families.NegativeBinomial(alpha=alpha))
results = model.fit()
predictions = results.predict(test).astype(int)
score = eval_measures.meanabs(predictions, test.total_cases)
if score < best_score:
best_alpha = alpha
best_score = score
# fit the final model
data = x_train.copy()
data['target'] = y_train
model_formula = data.columns[0]
for i in range(1, len(data.columns) - 1):
model_formula = model_formula + " + " + data.columns[i]
model_formula = data.columns[-1] + ' ~ ' + model_formula
# # Step 4: refit on entire dataset
model = smf.glm(formula=model_formula,
data=data,
family=sm.families.NegativeBinomial(alpha=best_alpha))
fitted_model = model.fit()
return fitted_model
def gradient_boosting(train_data, val_data):
params = {
'n_estimators': 800,
'max_depth': 5,
'min_samples_split': 3,
'learning_rate': 0.01,
'loss': 'ls'
}
clf = ensemble.GradientBoostingRegressor(**params)
train_label = train_data['total_cases']
train_feat = train_data.drop('total_cases', axis=1)
clf.fit(train_feat, train_label)
predictions = clf.predict(train_feat)
mae = eval_measures.meanabs(predictions, train_label)
#print("Training MAE: %.4f" % mae)
val_label = val_data['total_cases']
val_feat = val_data.drop('total_cases', axis=1)
val_predictions = clf.predict(val_feat)
mae = eval_measures.meanabs(val_predictions, val_label)
#print("Validation MAE: %.4f" % mae)
return clf
def evaluate(self):
"""
Calculates the MAE between the predicted and test ratings.
"""
predicted = self.get_full_rating_matrix()
real_ratings = []
predicted_ratings = []
for user, movie_ratings in self.test_set.iteritems():
for movie_id, rating in movie_ratings.iteritems():
predicted_user = predicted.get(user, None)
if not predicted_user:
continue
predicted_rating = predicted_user.get(movie_id, None)
if not predicted_rating:
continue
predicted_ratings.append(predicted_rating)
real_ratings.append(rating)
return meanabs(real_ratings, predicted_ratings)
def eval_metrics(forecast, observed):
'''Return forecast evaluation metrics.
Parameters
----------
forecast : pd.Series
Forecasted values.
observed : pd.Series
Observed values.
Return
------
mae : float
Mean Absolute Error metric.
rmserr : float
Root Mean Squared Error metric. Named rmserr to avoid
conflicting with statsmodels rmse function.
'''
return meanabs(forecast, observed), rmse(
forecast,
observed), (((forecast - observed).abs() / observed).mean()) * 100
def forecast_arima(df: pd.DataFrame, cols: list, with_graph: bool = True):
lag = 0
order = 1
moving_avg_model = 0
steps = 50
for col in cols:
model = ARIMA(df[col].iloc[:-steps],
order=(lag, order, moving_avg_model))
model_fit = model.fit()
model_for = model_fit.get_forecast(steps=steps, alpha=0.05)
print('\t==== Summary of forecast ARIMA(%d, %d, %d) ====\n' %
(lag, order, moving_avg_model))
print(model_for.summary_frame(), model_for.conf_int(), sep='\n')
print('RMSE: %f\nMAE: %f' %
(rmse(df[col][-50:], model_for.predicted_mean),
meanabs(df[col][-50:], model_for.predicted_mean)))
print()
if with_graph is True:
plt.figure(figsize=(12, 5))
plt.xlabel(col)
plt.title('Forecast for %s using ARIMA(%d, %d, %d)' %
(col, lag, order, moving_avg_model))
ax1 = model_for.predicted_mean.plot(color='blue',
grid=True,
label='Actual')
ax2 = df[col][-50:].plot(color='red',
grid=True,
secondary_y=True,
label='Estimated')
h1, l1 = ax1.get_legend_handles_labels()
h2, l2 = ax2.get_legend_handles_labels()
plt.legend(h1 + h2, l1 + l2, loc=2)
plt.show()
def TrainModel(self, DATA, args={}):
np.random.seed(1)
self, options = UpdateOptions(self, args)
self.Models = {}
self.Accuracy = []
DATA_X = DATA.iloc[:, :-1]
DATA_Y = DATA.iloc[:, -1]
models = {}
acc = []
for i in range(0, self.NumberOfModels):
newData = np.random.randint(DATA.shape[0], size=DATA.shape[0])
newTest = np.delete(np.arange(0, DATA.shape[0]),
pd.unique(newData))
data = DATA.iloc[newData, :].reset_index(drop=True)
models[i] = RandomForest()
models[i].TrainModel(data)
tst_X = DATA_X.iloc[newTest, :].reset_index(drop=True)
tst_Y = DATA_Y.iloc[newTest].reset_index(drop=True)
predictions = models[i].Predict(tst_X).astype(int)
acc.append(eval_measures.meanabs(predictions, tst_Y))
acc = np.asarray(acc)
for i in range(0, self.NumberOfOutModels):
index = acc.argmin()
self.Accuracy.append(acc[index])
acc[index] = acc.max()
self.Models[i] = models[index]
self.Accuracy = np.asarray(self.Accuracy)
# print(str(self.Accuracy.mean()))
return self.Accuracy.mean()
def MultipleRandFrorest(idf, K=50, nest=100, rnd=20):
df = idf.copy()
train_Y = df.total_cases
df.drop('total_cases', axis=1, inplace=True)
models = {}
acc = []
for i in range(0, K):
newData = np.random.randint(df.shape[0], size=df.shape[0])
newTest = np.delete(np.arange(0, df.shape[0]), np.unique(newData))
data_X = df.iloc[newData, :].reset_index(drop=True)
data_Y = train_Y.iloc[newData].reset_index(drop=True)
models[i] = RandomForestRegressor(n_estimators=nest, random_state=rnd)
models[i].fit(data_X, data_Y)
tst_X = df.iloc[newTest, :].reset_index(drop=True)
tst_Y = train_Y.iloc[newTest].reset_index(drop=True)
predictions = models[i].predict(tst_X).astype(int)
acc.append(eval_measures.meanabs(predictions, tst_Y))
acc = np.asarray(acc)
out_models = {}
out_ACC = []
for i in range(0, round(K)):
indx = acc.argmin()
out_ACC.append(acc[indx])
acc[indx] = 100
out_models[i] = models[indx]
out_ACC = np.asarray(out_ACC)
print(str(out_ACC.mean()))
return out_models
def main():
### parsing and Data pre-processing
# load the provided data
train_features_path = os.path.join(data_path, 'dengue_features_train.csv')
train_labels_path = os.path.join(data_path, 'dengue_labels_train.csv')
train_features = pd.read_csv(train_features_path, index_col=[0, 1, 2])
train_labels = pd.read_csv(train_labels_path, index_col=[0, 1, 2])
# Seperate data for San Juan
sj_train_features = train_features.loc['sj']
sj_train_labels = train_labels.loc['sj']
# Separate data for Iquitos
iq_train_features = train_features.loc['iq']
iq_train_labels = train_labels.loc['iq']
# Remove 'week_start_date' string.
sj_train_features.drop('week_start_date', axis=1, inplace=True)
iq_train_features.drop('week_start_date', axis=1, inplace=True)
#find NaN in data be unsatisfying and eliminate those ddata
sj_train_features.fillna(method='ffill', inplace=True)
iq_train_features.fillna(method='ffill', inplace=True)
### pre-processing data
sj_train, iq_train = preprocess_data(train_features_path,
labels_path=train_labels_path)
#print(sj_train.describe())
#print(iq_train.describe())
'''
sj_train_subtrain = sj_train.head(800)
sj_train_subtest = sj_train.tail(sj_train.shape[0] - 800)
iq_train_subtrain = iq_train.head(400)
iq_train_subtest = iq_train.tail(iq_train.shape[0] - 400)
'''
choose = rand.sample(range(0, sj_train.shape[0] - 1), 800)
val = [i for i in range(sj_train.shape[0]) if i not in choose]
sj_train_subtrain = sj_train.ix[choose]
sj_train_subtest = sj_train.ix[val]
choose = rand.sample(range(0, iq_train.shape[0] - 1), 400)
val = [i for i in range(iq_train.shape[0]) if i not in choose]
iq_train_subtrain = iq_train.ix[choose]
iq_train_subtest = iq_train.ix[val]
sj_best_model = get_best_model(sj_train_subtrain, sj_train_subtest, 'sj')
iq_best_model = get_best_model(iq_train_subtrain, iq_train_subtest, 'iq')
#Use K-fold to create cross validation data
kf = KFold(n_splits=12)
sj_score = []
for train_index, test_index in kf.split(sj_train):
#print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = sj_train.ix[train_index], sj_train.ix[test_index]
predictions = sj_best_model.predict(X_test).astype(int)
for i in range(predictions.shape[0] - 1, 3, -1):
predictions.ix[i] = predictions.ix[i - 4]
sj_score.append(eval_measures.meanabs(predictions, X_test.total_cases))
print("Mean of {} cross validation of sj_score is {} (+/- {})".format(
kf.get_n_splits(sj_train), np.mean(sj_score), np.std(sj_score)))
print(sj_score)
iq_score = []
for train_index, test_index in kf.split(iq_train):
#print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = iq_train.ix[train_index], iq_train.ix[test_index]
predictions = iq_best_model.predict(X_test).astype(int)
#print(predictions)
for i in range(predictions.shape[0] - 1, 0, -1):
predictions.ix[i] = predictions.ix[i - 1]
#print(predictions)
iq_score.append(eval_measures.meanabs(predictions, X_test.total_cases))
print(iq_score)
print("Mean of {} cross validation of iq_score is {} (+/- {})".format(
kf.get_n_splits(iq_train), np.mean(iq_score), np.std(iq_score)))
figs, axes = plt.subplots(nrows=2, ncols=1)
# plot sj
sj_train['fitted'] = sj_best_model.fittedvalues
sj_train.fitted.plot(ax=axes[0], label="Predictions")
sj_train.total_cases.plot(ax=axes[0], label="Actual")
# plot iq
iq_train['fitted'] = iq_best_model.fittedvalues
iq_train.fitted.plot(ax=axes[1], label="Predictions")
iq_train.total_cases.plot(ax=axes[1], label="Actual")
plt.suptitle("Dengue Predicted Cases vs. Actual Cases")
plt.legend()
plt.show()
test_features_path = os.path.join(data_path, 'dengue_features_test.csv')
sj_test, iq_test = preprocess_data(test_features_path)
sj_predictions = sj_best_model.predict(sj_test).astype(int)
for i in range(sj_predictions.shape[0] - 1, 3, -1):
sj_predictions.ix[i] = sj_predictions.ix[i - 4]
iq_predictions = iq_best_model.predict(iq_test).astype(int)
for i in range(iq_predictions.shape[0] - 1, 0, -1):
iq_predictions.ix[i] = iq_predictions.ix[i - 1]
sample_path = os.path.join(data_path, 'submission_format.csv')
submission = pd.read_csv(sample_path, index_col=[0, 1, 2])
submission.total_cases = np.concatenate([sj_predictions, iq_predictions])
submission.to_csv("./data/benchmark_shift.csv")
def CalculatePerformance(self, result, target):
if self.NegativeBinomial == {}:
return None
else:
return eval_measures.meanabs(result, target)
# print('{} {} {}'.format(
# valid_data[column].index.values[IDX], valid_data[column].iloc[IDX], forecast_data[column].iloc[IDX]))
ax1.plot(valid_data[column].index,
forecast_data[column],
linewidth=0.5)
# log the MSE and MAE
logging.info(
'Mean square error for {} forecast for data order {} for column {} : {}'
.format(forecast_type[forecast], order_type[order], column,
mse(valid_data[column], forecast_data[column])))
logging.info(
'Absolute square error for {} forecast for data order {} for column {} : {}'
.format(forecast_type[forecast], order_type[order], column,
meanabs(valid_data[column], forecast_data[column])))
forecast_cnt = len(valid_data.index.values)
correct_forecast_direction = 0
for data_idx in range(forecast_cnt):
if (valid_data[column][data_idx] >
0) == (forecast_data[column][data_idx] > 0):
correct_forecast_direction = correct_forecast_direction + 1
logging.info(
'Percent of valid data that is incerease from previous day {}'.
format(valid_data[column].gt(0).sum() / forecast_cnt))
logging.info(
'Percent of forecast that matches valid direction {}'.format(
correct_forecast_direction / forecast_cnt))
# write out the results to csv files for post processing
output_file = open(
def evaluation(validation_data: pd.Series, forecast_ets: pd.Series, forecast_arima: pd.Series, forecast_xgboost: pd.Series, forecast_snaive: pd.Series, forecast_drift: pd.Series, forecast_average: pd.Series, verbose: bool):
print("\tPrediction model\t\t|\tRMSE\t\t\t\t|\tMAE\t\t\t\t\t|\tSeasonal MASE\t\t|\tSMAPE")
print("\t-------------------------------------------------------------------------------------------------")
sn = [
rmse([float(x) for x in validation_data.values], forecast_snaive),
meanabs([float(x) for x in validation_data.values], forecast_snaive),
eval.mase(validation_data.values, forecast_snaive, 5),
eval.smape(validation_data.values, forecast_snaive)
]
if verbose:
print("\tSeasonal Naive", end="\t\t\t|\t")
print(sn[0], end="\t|\t")
print(sn[1], end="\t|\t")
print(sn[2], end="\t|\t")
print(sn[3])
df = [
rmse([float(x) for x in validation_data.values], forecast_drift),
meanabs([float(x) for x in validation_data.values], forecast_drift),
eval.mase(validation_data.values, forecast_drift, 5),
eval.smape(validation_data.values, forecast_drift)
]
if verbose:
print("\tDrift", end="\t\t\t\t\t|\t")
print(df[0], end="\t|\t")
print(df[1], end="\t|\t")
print(df[2], end="\t|\t")
print(df[3])
av = [
rmse([float(x) for x in validation_data.values], forecast_average),
meanabs([float(x) for x in validation_data.values], forecast_average),
eval.mase(validation_data.values, forecast_average, 5),
eval.smape(validation_data.values, forecast_average)
]
if verbose:
print("\tAverage", end="\t\t\t\t\t|\t")
print(av[0], end="\t|\t")
print(av[1], end="\t|\t")
print(av[2], end="\t|\t")
print(av[3])
xgb = [
rmse([float(x) for x in validation_data.values], forecast_xgboost),
meanabs([float(x) for x in validation_data.values], forecast_xgboost),
eval.mase(validation_data.values, forecast_xgboost, 5),
eval.smape(validation_data.values, forecast_xgboost)
]
if verbose:
print("\tXGBoost Regression", end="\t\t|\t")
print(xgb[0], end="\t|\t")
print(xgb[1], end="\t|\t")
print(xgb[2], end="\t|\t")
print(xgb[3])
ets = [
rmse([float(x) for x in validation_data.values], forecast_ets),
meanabs([float(x) for x in validation_data.values], forecast_ets),
eval.mase(validation_data.values, forecast_ets, 5),
eval.smape(validation_data.values, forecast_ets)
]
if verbose:
print("\tExponentialSmoothing", end="\t|\t")
print(ets[0], end="\t|\t")
print(ets[1], end="\t|\t")
print(ets[2], end="\t|\t")
print(ets[3])
ar = [
rmse([float(x) for x in validation_data.values], forecast_arima),
meanabs([float(x) for x in validation_data.values], forecast_arima),
eval.mase(validation_data.values, forecast_arima, 5),
eval.smape(validation_data.values, forecast_arima)
]
if verbose:
print("\tARIMA", end="\t\t\t\t\t|\t")
print(ar[0], end="\t|\t")
print(ar[1], end="\t|\t")
print(ar[2], end="\t|\t")
print(ar[3])
eval_results = DataFrame ([sn, df, av, xgb, ets, ar], index = ['seasonal_naive','drift','average','xgboost','ets','arima'],columns = ['RMSE','MAE','MASE', 'sMAPE'])
return eval_results
def CalculatePerformance(self, result, target):
if self.Models == {}:
return None
else:
return eval_measures.meanabs(result, target)
from statsmodels.tsa.stattools import grangercausalitytests
grangercausalitytests(df3[['a', 'd']], maxlag=5)
grangercausalitytests(df3[['b', 'd']], maxlag=5)
np.random.seed(42)
df = pd.DataFrame(np.random.randint(20, 30, (50, 2)),
columns=['test', 'predictions'])
df.head()
df.plot(figsize=(12, 8))
from statsmodels.tools.eval_measures import mse, rmse, meanabs
mse(df['test'], df['predictions'])
rmse(df['test'], df['predictions'])
meanabs(df['test'], df['predictions'])
df1.head()
df1.index
from statsmodels.graphics.tsaplots import month_plot, quarter_plot
month_plot(df1['Pass_K'])
df1q = df1['Pass_K'].resample(rule='Q').sum()
quarter_plot(df1q)
def get_best_model_sj(train, test):
# Step 1: specify the form of the model
#CHANGE HERE ---- SJ FEATURES
model_formula = "total_cases ~ 1 + " \
"reanalysis_specific_humidity_g_per_kg + " \
"reanalysis_dew_point_temp_k + " \
"station_avg_temp_c + " \
"station_max_temp_c + " \
"reanalysis_air_temp_k + " \
"reanalysis_relative_humidity_percent + " \
"reanalysis_relative_humidity_percent_2 + " \
"reanalysis_relative_humidity_percent_3 + " \
"reanalysis_precip_amt_kg_per_m2_2 + " \
"reanalysis_precip_amt_kg_per_m2_3 + " \
"reanalysis_specific_humidity_g_per_kg_2 + " \
"reanalysis_specific_humidity_g_per_kg_3 + " \
"reanalysis_dew_point_temp_k_2 + " \
"reanalysis_dew_point_temp_k_3 + " \
"reanalysis_dew_point_temp_k_4 + " \
"reanalysis_air_temp_k_2 + " \
"reanalysis_air_temp_k_4 + " \
"reanalysis_air_temp_k_5 + " \
"reanalysis_air_temp_k_6 + " \
"reanalysis_air_temp_k_7 + " \
"reanalysis_air_temp_k_8 + " \
"station_max_temp_c_3 + " \
"station_max_temp_c_4 + " \
"station_max_temp_c_5 + " \
"station_max_temp_c_6 + " \
"station_max_temp_c_2 + " \
"reanalysis_sat_precip_amt_mm_2 + " \
"precipitation_amt_mm_2 + " \
"precipitation_amt_mm_3"
grid = 10**np.arange(-8, -3, dtype=np.float64)
best_alpha = []
best_score = 1000
# Step 2: Find the best hyper parameter, alpha
for alpha in grid:
model = smf.glm(formula=model_formula,
data=train,
family=sm.families.NegativeBinomial(alpha=alpha))
results = model.fit()
predictions = results.predict(test).astype(int)
score = eval_measures.meanabs(predictions, test.total_cases)
if score < best_score:
best_alpha = alpha
best_score = score
print('best alpha = ', best_alpha)
print('best score = ', best_score)
# Step 3: refit on entire dataset
full_dataset = pd.concat([train, test])
model = smf.glm(formula=model_formula,
data=full_dataset,
family=sm.families.NegativeBinomial(alpha=best_alpha))
fitted_model = model.fit()
return fitted_model
'2': np.round(sdarbict1, 4)
},
]
mstable = pd.DataFrame(msdata)
print('')
print('== ARIMA Model Selection ==')
print('')
print(mstable)
print('')
##########################################
# 3.8. ARIMA Models Forecasting Accuracy
# 3.8.1. Multi-Steps Forecast
rwdmae1 = fa.meanabs(rwdf1, spyf)
rwdrmse1 = fa.rmse(rwdf1, spyf)
darmae1 = fa.meanabs(darf1, spyf)
darrmse1 = fa.rmse(darf1, spyf)
srwdmae1 = fa.meanabs(srwdf1, spyf)
srwdrmse1 = fa.rmse(srwdf1, spyf)
sdarmae1 = fa.meanabs(sdarf1, spyf)
sdarrmse1 = fa.rmse(sdarf1, spyf)
fadata1 = [
{
'0': '',
'1': 'MAE',
'2': 'RMSE'
},
{
def main():
### parsing and Data pre-processing
# load the provided data
train_features_path = os.path.join(data_path, 'dengue_features_train.csv')
train_labels_path = os.path.join(data_path, 'dengue_labels_train.csv')
### pre-processing data
sj_train, iq_train = preprocess_data(train_features_path,
labels_path=train_labels_path)
#print(sj_train.describe())
#print(iq_train.describe())
###Define the xgb parameters
xgb_params = {
'eta': 0.05,
'max_depth': 5,
'subsample': 0.7,
'colsample_bytree': 0.7,
'objective': 'reg:linear',
'eval_metric': 'rmse',
'silent': 1
}
num_boost_rounds = 1000
##Use K-fold to create cross validation data
kf = KFold(n_splits=6)
##Do the stacking by adding 5 dataframes 'negbi', 'gb', 'xgb','adaboost','extratree' ,'bagging'which store the training prediction
sj_train = sj_train.assign(negbi=0)
sj_train = sj_train.assign(gb=0)
sj_train = sj_train.assign(xgb=0)
sj_train = sj_train.assign(abr=0)
sj_train = sj_train.assign(etr=0)
sj_train = sj_train.assign(br=0)
loop = 1
for train_index, val_index in kf.split(
sj_train
): #The index will be split into [train_index] and [val_index]
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
###(1)neg_binomial method
sj_neg_model = get_best_model(X_train, X_val, 'sj')
predictions_neg = sj_neg_model.predict(X_val).astype(int)
#Shift the prediction manually
for i in range(predictions_neg.shape[0] - 1, 3, -1):
predictions_neg.ix[i] = predictions_neg.ix[i - 4]
###(2)gradient boosting method
sj_gb_model = gradient_boosting(
X_train.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1),
X_val.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1))
predictions_gb = sj_gb_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(3)xgboost method
dtrain = xgb.DMatrix(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
dval = xgb.DMatrix(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
sj_xgb_model = xgb.train(dict(xgb_params, silent=0),
dtrain,
num_boost_round=num_boost_rounds)
predictions_xgb = sj_xgb_model.predict(dval).astype(int)
###(4)Adaboost regressor method
sj_abr_model = ABR(n_estimators=800,
learning_rate=0.08,
loss='linear',
random_state=0)
sj_abr_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_abr = sj_abr_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###(5)Extra tree regressor method
sj_etr_model = ETR(n_estimators=800,
max_depth=4,
random_state=0,
verbose=1)
sj_etr_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_etr = sj_etr_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###(6) Bagging Regressor method
sj_br_model = BR(n_estimators=800,
oob_score=False,
n_jobs=5,
random_state=0,
verbose=1)
sj_br_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_br = sj_br_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###Store the result in sj_train predictions_neg -> 'negbi', predictions_gb -> 'gb'
print(
"Adding the result of the predictions to sj training data({}/{})".
format(loop, 6))
for idx, index in enumerate(val_index):
sj_train['negbi'].ix[index] = predictions_neg.ix[idx]
sj_train['gb'].ix[index] = predictions_gb[idx]
sj_train['xgb'].ix[index] = predictions_xgb[idx]
sj_train['abr'].ix[index] = predictions_abr[idx]
sj_train['etr'].ix[index] = predictions_etr[idx]
sj_train['br'].ix[index] = predictions_br[idx]
loop += 1
iq_train = iq_train.assign(negbi=0)
iq_train = iq_train.assign(gb=0)
iq_train = iq_train.assign(xgb=0)
iq_train = iq_train.assign(abr=0)
iq_train = iq_train.assign(etr=0)
iq_train = iq_train.assign(br=0)
loop = 1
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
###(1)neg_binomial method
iq_neg_model = get_best_model(X_train, X_val, 'iq')
predictions_neg = iq_neg_model.predict(X_val).astype(int)
#Shift the prediction manually
for i in range(predictions_neg.shape[0] - 1, 0, -1):
predictions_neg.ix[i] = predictions_neg.ix[i - 1]
###(2)gradient boosting method
iq_gb_model = gradient_boosting(
X_train.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1),
X_val.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1))
predictions_gb = iq_gb_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(3)xgb method
dtrain = xgb.DMatrix(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
dval = xgb.DMatrix(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
iq_xgb_model = xgb.train(dict(xgb_params, silent=0),
dtrain,
num_boost_round=num_boost_rounds)
predictions_xgb = iq_xgb_model.predict(dval).astype(int)
###(4)Adaboost regressor method
iq_abr_model = ABR(n_estimators=800,
learning_rate=0.08,
loss='linear',
random_state=0)
iq_abr_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_abr = iq_abr_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###(5)Extra tree regressor method
iq_etr_model = ETR(n_estimators=800,
max_depth=4,
random_state=0,
verbose=1)
iq_etr_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_etr = iq_etr_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###(6) Bagging Regressor method
iq_br_model = BR(n_estimators=800,
oob_score=False,
n_jobs=5,
random_state=0,
verbose=1)
iq_br_model.fit(
X_train.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1), X_train['total_cases'])
predictions_br = iq_br_model.predict(
X_val.drop(
['total_cases', 'negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1))
###Store the result in iq_train predictions_neg -> 'negbi', predictions_gb -> 'gb'
print(
"Adding the result of the predictions to iq training data({}/{})".
format(loop, 6))
for idx, index in enumerate(val_index):
iq_train['negbi'].ix[index] = predictions_neg.ix[idx]
iq_train['gb'].ix[index] = predictions_gb[idx]
iq_train['xgb'].ix[index] = predictions_xgb[idx]
iq_train['abr'].ix[index] = predictions_abr[idx]
iq_train['etr'].ix[index] = predictions_etr[idx]
iq_train['br'].ix[index] = predictions_br[idx]
loop += 1
###Now the training data looks like [feature, total_cases, negbi, gb, xgb]
##Accessing testing data
test_features_path = os.path.join(data_path, 'dengue_features_test.csv')
sj_test, iq_test = preprocess_data(test_features_path)
##Like training, add 'negbi' and 'gb' to the testing dataframe
sj_test = sj_test.assign(negbi=0)
sj_test = sj_test.assign(gb=0)
sj_test = sj_test.assign(xgb=0)
sj_test = sj_test.assign(abr=0)
sj_test = sj_test.assign(etr=0)
sj_test = sj_test.assign(br=0)
##(1)neg_binomial prediction
sj_predictions_neg = sj_neg_model.predict(sj_test).astype(int)
for i in range(sj_predictions_neg.shape[0] - 1, 3, -1):
sj_predictions_neg.ix[i] = sj_predictions_neg.ix[i - 4]
##(2)gradient boosting prediction
sj_predictions_gb = sj_gb_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
##(3)xgb prediction
dtest = xgb.DMatrix(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1))
sj_predictions_xgb = sj_xgb_model.predict(dtest).astype(int)
###(4)Adaboost regressor method
sj_predictions_abr = sj_br_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(5)extra tree regressor method
sj_predictions_etr = sj_etr_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(6)bagging regressor method
sj_predictions_br = sj_br_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
print("Adding predictions as features to sj testing data...")
for i in range(len(sj_test['negbi'])
): #Add the prediction to the corresponding column
sj_test['negbi'].ix[i] = sj_predictions_neg.ix[i]
sj_test['gb'].ix[i] = sj_predictions_gb[i]
sj_test['xgb'].ix[i] = sj_predictions_xgb[i]
sj_test['abr'].ix[i] = sj_predictions_abr[i]
sj_test['etr'].ix[i] = sj_predictions_etr[i]
sj_test['br'].ix[i] = sj_predictions_br[i]
##Same process as city sj
iq_test = iq_test.assign(negbi=0)
iq_test = iq_test.assign(gb=0)
iq_test = iq_test.assign(xgb=0)
iq_test = iq_test.assign(abr=0)
iq_test = iq_test.assign(etr=0)
iq_test = iq_test.assign(br=0)
###(1)neg_binomial prediction
iq_predictions_neg = iq_neg_model.predict(iq_test).astype(int)
for i in range(iq_predictions_neg.shape[0] - 1, 0, -1):
iq_predictions_neg.ix[i] = iq_predictions_neg.ix[i - 1]
##(2)gradient boosting prediction
iq_predictions_gb = iq_gb_model.predict(
iq_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
##(3)xgb prediction
dtest = xgb.DMatrix(
iq_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'], axis=1))
iq_predictions_xgb = iq_xgb_model.predict(dtest).astype(int)
###(4)Adaboost regressor method
iq_predictions_abr = iq_abr_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(5)extra tree regressor method
iq_predictions_etr = iq_etr_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
###(6)bagging regressor method
iq_predictions_br = iq_br_model.predict(
sj_test.drop(['negbi', 'gb', 'xgb', 'abr', 'etr', 'br'],
axis=1)).astype(int)
print("Adding predictions as features to iq testing data...")
for i in range(len(iq_test['negbi'])):
iq_test['negbi'].ix[i] = iq_predictions_neg.ix[i]
iq_test['gb'].ix[i] = iq_predictions_gb[i]
iq_test['xgb'].ix[i] = iq_predictions_xgb[i]
iq_test['abr'].ix[i] = iq_predictions_abr[i]
iq_test['etr'].ix[i] = iq_predictions_etr[i]
iq_test['br'].ix[i] = iq_predictions_br[i]
##use new information to run a linear regression
print("Building linear regression model...")
#Now the linear regression model uses (X = [features, negbi, gb, xgb], y = total_cases )to train(fit)
sj_lr = LR()
sj_lr.fit(sj_train.drop('total_cases', axis=1), sj_train['total_cases'])
iq_lr = LR()
iq_lr.fit(iq_train.drop('total_cases', axis=1), iq_train['total_cases'])
#Calculate the k-fold validation error
sj_score = []
for train_index, val_index in kf.split(sj_train):
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
train_predict = np.array(
sj_lr.predict(X_val.drop('total_cases', axis=1))).astype(int)
sj_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of sj_score is {} (+/- {})".format(
kf.get_n_splits(sj_train), np.mean(sj_score), np.std(sj_score)))
iq_score = []
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
train_predict = np.array(
iq_lr.predict(X_val.drop('total_cases', axis=1))).astype(int)
iq_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of iq_score is {} (+/- {})".format(
kf.get_n_splits(iq_train), np.mean(iq_score), np.std(iq_score)))
##Use the model sj_lr and iq_lr trained before to predict the testing data
print("Predicting testing data...")
sj_predictions = sj_lr.predict(sj_test)
iq_predictions = iq_lr.predict(iq_test)
sj_predictions = np.array(sj_predictions).astype(int)
iq_predictions = np.array(iq_predictions).astype(int)
print("Creating submit file...")
##Use submission_format as template to write the answer
sample_path = os.path.join(data_path, 'submission_format.csv')
submission = pd.read_csv(sample_path, index_col=[0, 1, 2])
submission.total_cases = np.concatenate([sj_predictions, iq_predictions])
submission.to_csv("./data/stacking_6_less_feature.csv")
'''
# Fix S% issue with "--" and multiply S% by 2 if d-man
while i < regression_data['TOI/GP'].size:
if regression_data['S%'][i] == "--":
shootingp.append(0)
else:
shotp = float(regression_data['S%'][i])
shootingp.append(shotp)
if regression_data['Pos'][i] == "D" and regression_data['S%'][i] != "--":
shootingp.append(float(regression_data['S%'][i]) * 2)
i = i + 1
shootingp_array = np.array(shootingp)
regression_data['S%'] = pd.Series(shootingp_array)
variables = regression_data[['G', 'A', 'TOI/GP', 'PPP']].values
salary = regression_data['AAV'].values
var_train, var_test, sal_train, sal_test = train_test_split(variables,
salary,
test_size=0.2,
random_state=5)
lin_model = sm.OLS(sal_train, var_train)
result = lin_model.fit()
sal_pred = result.predict(var_test)
print(result.summary())
print("Mean Absolute Error: " + str(meanabs(sal_test, sal_pred, axis=0)))
def main():
### parsing and Data pre-processing
# load the provided data
train_features_path = os.path.join(data_path, 'dengue_features_train.csv')
train_labels_path = os.path.join(data_path, 'dengue_labels_train.csv')
### pre-processing data
sj_train, iq_train = preprocess_data(train_features_path,
labels_path=train_labels_path)
#print(sj_train.describe())
#print(iq_train.describe())
choose = rand.sample(range(0, sj_train.shape[0] - 1), 800)
val = [i for i in range(sj_train.shape[0]) if i not in choose]
sj_train_subtrain = sj_train.ix[choose]
sj_train_subtest = sj_train.ix[val]
sj_etr = ETR(n_estimators=2000, max_depth=3, criterion='mae', verbose=1)
sj_etr.fit(sj_train_subtrain.drop('total_cases', axis=1),
sj_train_subtrain['total_cases'])
##The model generate by neg_binomial with best alpha on val_set chosen before
kf = KFold(n_splits=12)
sj_model_list = []
sj_err_list = []
loop = 1
for train_index, val_index in kf.split(
sj_train
): #The index will be split into [train_index] and [val_index]
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
#sj_etr = ETR(n_estimators = 2000, max_depth = 3,criterion = 'mae',verbose = 1)
#sj_etr.fit(X_train.drop(['station_avg_temp_c','total_cases'],axis = 1),X_train['total_cases'])
predictions = sj_etr.predict(X_val.drop('total_cases', axis=1))
sj_err_list.append(
eval_measures.meanabs(predictions, X_val.total_cases))
#sj_model_list.append(sj_etr)
loop += 1
print(sj_err_list)
#argmax = sorted(range(len(sj_err_list)), key=lambda x: sj_err_list[x])[0]
#print(argmax)
#sj_best_model = sj_model_list[argmax]
sj_best_model = sj_etr
#print(sj_best_model.feature_importances_)
choose = rand.sample(range(0, iq_train.shape[0] - 1), 400)
val = [i for i in range(iq_train.shape[0]) if i not in choose]
iq_train_subtrain = iq_train.ix[choose]
iq_train_subtest = iq_train.ix[val]
iq_etr = ETR(n_estimators=2000, max_depth=3, criterion='mae', verbose=1)
iq_etr.fit(iq_train_subtrain.drop('total_cases', axis=1),
iq_train_subtrain['total_cases'])
iq_model_list = []
iq_err_list = []
loop = 1
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
#iq_etr = ETR(n_estimators = 2000, max_depth = 3,criterion = 'mae',verbose = 1)
#iq_etr.fit(X_train.drop(['station_min_temp_c','total_cases'],axis = 1),X_train['total_cases'])
predictions = iq_etr.predict(X_val.drop('total_cases', axis=1))
iq_err_list.append(
eval_measures.meanabs(predictions, X_val.total_cases))
#iq_model_list.append(iq_etr)
loop += 1
print(iq_err_list)
#argmax = sorted(range(len(iq_err_list)), key=lambda x: iq_err_list[x])[0]
#print(argmax)
#iq_best_model = iq_model_list[argmax]
iq_best_model = iq_etr
#print(iq_best_model.feature_importances_)
##Accessing testing data
test_features_path = os.path.join(data_path, 'dengue_features_test.csv')
sj_test, iq_test = preprocess_data(test_features_path)
#Calculate the k-fold validation error
sj_score = []
for train_index, val_index in kf.split(sj_train):
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
train_predict = np.array(
sj_best_model.predict(X_val.drop('total_cases',
axis=1))).astype(int)
sj_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of sj_score is {} (+/- {})".format(
kf.get_n_splits(sj_train), np.mean(sj_score), np.std(sj_score)))
iq_score = []
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
train_predict = np.array(
iq_best_model.predict(X_val.drop('total_cases',
axis=1))).astype(int)
iq_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of iq_score is {} (+/- {})".format(
kf.get_n_splits(iq_train), np.mean(iq_score), np.std(iq_score)))
##Use the model sj_lr and iq_lr trained before to predict the testing data
print("Predicting testing data...")
sj_predictions = sj_best_model.predict(sj_test)
iq_predictions = iq_best_model.predict(iq_test)
sj_predictions = np.round(sj_predictions).astype(int)
iq_predictions = np.round(iq_predictions).astype(int)
print("Creating submit file...")
##Use submission_format as template to write the answer
sample_path = os.path.join(data_path, 'submission_format.csv')
submission = pd.read_csv(sample_path, index_col=[0, 1, 2])
submission.total_cases = np.concatenate([[28], [25], [34], sj_predictions,
[8], [6], [10], iq_predictions])
submission.to_csv("./data/ext_final_new.csv")
'''
def main():
### parsing and Data pre-processing
# load the provided data
train_features_path = os.path.join(data_path, 'dengue_features_train.csv')
train_labels_path = os.path.join(data_path, 'dengue_labels_train.csv')
### pre-processing data
sj_train, iq_train = preprocess_data(train_features_path,
labels_path=train_labels_path)
#print(sj_train.describe())
#print(iq_train.describe())
kf = KFold(n_splits=6)
sj_model_list = []
sj_err_list = []
loop = 1
for train_index, val_index in kf.split(
sj_train
): #The index will be split into [train_index] and [val_index]
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
sj_etr = ETR(n_estimators=800, max_depth=4, random_state=0, verbose=1)
sj_etr.fit(X_train.drop('total_cases', axis=1), X_train['total_cases'])
predictions = sj_etr.predict(X_val.drop('total_cases', axis=1))
sj_err_list.append(
eval_measures.meanabs(predictions, X_val.total_cases))
sj_model_list.append(sj_etr)
loop += 1
print(sj_err_list)
argmax = sorted(range(len(sj_err_list)), key=lambda x: sj_err_list[x])[0]
print(argmax)
sj_best_model = sj_model_list[argmax]
iq_model_list = []
iq_err_list = []
loop = 1
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
iq_etr = ETR(n_estimators=400, max_depth=4, random_state=0)
iq_etr.fit(X_train.drop('total_cases', axis=1), X_train['total_cases'])
predictions = iq_etr.predict(X_val.drop('total_cases', axis=1))
iq_err_list.append(
eval_measures.meanabs(predictions, X_val.total_cases))
iq_model_list.append(iq_etr)
loop += 1
print(iq_err_list)
argmax = sorted(range(len(iq_err_list)), key=lambda x: iq_err_list[x])[0]
print(argmax)
iq_best_model = iq_model_list[argmax]
##Accessing testing data
test_features_path = os.path.join(data_path, 'dengue_features_test.csv')
sj_test, iq_test = preprocess_data(test_features_path)
#Calculate the k-fold validation error
sj_score = []
for train_index, val_index in kf.split(sj_train):
X_train, X_val = sj_train.ix[train_index], sj_train.ix[val_index]
train_predict = np.array(
sj_best_model.predict(X_val.drop('total_cases',
axis=1))).astype(int)
sj_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of sj_score is {} (+/- {})".format(
kf.get_n_splits(sj_train), np.mean(sj_score), np.std(sj_score)))
iq_score = []
for train_index, val_index in kf.split(iq_train):
X_train, X_val = iq_train.ix[train_index], iq_train.ix[val_index]
train_predict = np.array(
iq_best_model.predict(X_val.drop('total_cases',
axis=1))).astype(int)
iq_score.append(eval_measures.meanabs(train_predict,
X_val.total_cases))
print("Mean of {} cross validation of iq_score is {} (+/- {})".format(
kf.get_n_splits(iq_train), np.mean(iq_score), np.std(iq_score)))
##Use the model sj_lr and iq_lr trained before to predict the testing data
print("Predicting testing data...")
sj_predictions = sj_best_model.predict(sj_test)
iq_predictions = iq_best_model.predict(iq_test)
sj_predictions = np.array(sj_predictions).astype(int)
iq_predictions = np.array(iq_predictions).astype(int)
print("Creating submit file...")
##Use submission_format as template to write the answer
sample_path = os.path.join(data_path, 'submission_format.csv')
submission = pd.read_csv(sample_path, index_col=[0, 1, 2])
submission.total_cases = np.concatenate([sj_predictions, iq_predictions])
submission.to_csv("./data/ext_new.csv")
'''