epochs = 10000
batch_size = 64
layer_dims = {"in": 13, "fc1": 10, "fc2": 10, "fc3": 10, "fc4": 10, "out": 1}
dtype = torch.Tensor
def rmsle(y_pred, y_true):
log_err = torch.log(y_pred + 1) - torch.log(y_true + 1)
squared_le = torch.pow(log_err, 2)
mean_sle = torch.mean(squared_le)
root_msle = torch.sqrt(mean_sle)
return (root_msle)
if __name__ == '__main__':
_, _, _, X_train, Y_train, Y_train_log, X_val, Y_val, X_test, test_date_df = du.get_processed_df(
'data/train.csv', 'data/test.csv')
train_data_size = X_train.shape[0]
print(train_data_size)
steps_in_epoch = train_data_size // batch_size
#Dividing data to train and val datasets, conversion from DF to numpyarray
X_train = np.array(X_train)
Y_train = np.array(Y_train)
Y_train_log = np.array(Y_train_log)
X_val = np.array(X_val)
Y_val = np.array(Y_val)
X_test = np.array(X_test)
# Create random Tensors to hold inputs and outputs, and wrap them in Variables.
X_train = Variable(torch.Tensor(X_train))
reverse_opts = [False]
tested_params = Cs
val_error_hist = np.zeros(len(tested_params))
train_error_hist = np.zeros(len(tested_params))
# Definitions of other kernels one may want to use
# svr_lin = SVR(kernel='linear', C=1000)
# svr_poly = SVR(kernel='poly', C=1000, degree=2, gamma=gamma)
for i, C in enumerate(tested_params):
for name in ["Gaussian"]:
for reverse in reverse_opts:
#Getting seperate train and val datasets to control data distribution
#train_x,train_y,Y_train_log,val_x,val_y = du.get_sep_datasets(datasetX,datasetY,TRAIN_SIZE,reverse_data_order=reverse)
df_x, _, df_y_log, train_x, train_y, train_y_log, val_x, val_y, test_x, test_date_df = du.get_processed_df(
'data/train.csv', 'data/test.csv')
#Training our regression model
regressor = SVR(kernel='rbf', C=C, gamma=gamma)
#regressor.fit(X_train, Y_train_log)
regressor.fit(train_x, train_y_log)
#Making predictions on train set
predictions_train_log = regressor.predict(train_x)
predictions_train = np.exp(predictions_train_log) - 1
predictions_train = np.maximum(0, predictions_train)
train_error = rmsle(predictions_train, train_y)
train_error_hist[i] += train_error
# Making predictions on val set
predictions_val_log = regressor.predict(val_x)
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from data_utils import DataUtils as du
def get_rmsle(y_pred, y_actual):
diff = np.log(y_pred + 1) - np.log(y_actual + 1)
mean_error = np.square(diff).mean()
return np.sqrt(mean_error)
if __name__ == '__main__':
df_x, _, df_y_log, train_x, train_y, train_y_log, val_x, val_y, test_x, test_date_df = du.get_processed_df(
'../data/train.csv',
'../data/test.csv',
output_cols=['registered', 'casual', 'count'],
model="rrf",
normalize=False)
train_y_log_reg = train_y_log['registered'].as_matrix()
train_y_log_cas = train_y_log['casual'].as_matrix()
train_y = train_y['count'].as_matrix()
max_depth_params = np.arange(1, 35, 1)
max_depth = 20
n_estimators_params = np.arange(1, 1000, 10)
n_estimators = 300
min_split_params = np.arange(12, 13, 1)
min_split = 12
tested_params = min_split_params
TOTAL_DATASET_SIZE = 10887
def rmsle(y_true, y_pred):
y_count_pred = KB.sum(y_pred, axis=1)
y_count_true = KB.sum(y_true, axis=1)
return KB.sqrt(
KB.mean(KB.square(KB.log(y_count_pred + 1) -
KB.log(y_count_true + 1))))
if __name__ == '__main__':
output_columns = ['registered', 'casual']
df_x, _, df_y_log, train_x, train_y, train_y_log, val_x, val_y, test_x, test_date_df = \
du.get_processed_df('../data/train.csv', '../data/test.csv',output_cols=output_columns, model = "rrf",randomize=True)
print("Dataset loaded, train_setX:", train_x.shape, ", train_setY:",
train_y.shape, ", val_setX:", val_x.shape, ", val_setY:",
val_y.shape)
df_x = np.array(df_x)
df_y_log = np.array(df_y_log)
train_x = np.array(train_x)
train_y = np.array(train_y)
train_y_log = np.array(train_y_log)
val_x = np.array(val_x)
val_y = np.array(val_y)
val_y = np.reshape(val_y, newshape=(val_y.shape[0], 1))
test_x = np.array(test_x)
test_error = 1000
def rmsle(y_pred, y_true):
log_err = (np.log(y_pred + 1) - np.log(y_true + 1))
squared_le = np.power(log_err, 2)
mean_sle = np.mean(squared_le)
root_msle = np.sqrt(mean_sle)
return (root_msle)
if __name__ == '__main__':
df_x, df_y, df_y_log, train_x, train_y, train_y_log, val_x, val_y, test_x, test_date_df = du.get_processed_df(
'../data/train.csv',
'../data/test.csv',
output_cols=['count'],
normalize=False)
val_y = np.reshape(val_y.as_matrix(), newshape=(val_y.shape[0], 1))
k_parameters = range(start_k_neighbours,
start_k_neighbours + num_k_neighbours)
for i, k in enumerate(k_parameters):
# Training Knn regressor
knn_regressor = KNeighborsRegressor(n_neighbors=k, weights='uniform')
knn_regressor.fit(train_x, train_y_log)
# Making predictions on train set
predictions_train_log = knn_regressor.predict(train_x)
def get_predicions(model_reg, model_cas, model_name):
df_x, _, df_y_log, train_x, train_y, train_y_log, val_x, val_y, test_x, test_date_df = du.get_processed_df(
'../data/train.csv',
'../data/test.csv',
output_cols=['registered', 'casual', 'count'],
model=model_name,
normalize=False)
y_pred_val_reg = np.exp(model_reg.predict(val_x)) - 1
y_pred_val_cas = np.exp(model_cas.predict(val_x)) - 1
y_pred_train_reg = np.exp(model_reg.predict(train_x)) - 1
y_pred_train_cas = np.exp(model_cas.predict(train_x)) - 1
y_pred_test_reg = np.exp(model_reg.predict(test_x)) - 1
y_pred_test_cas = np.exp(model_cas.predict(test_x)) - 1
y_pred_val = np.round(y_pred_val_reg + y_pred_val_cas)
y_pred_val[y_pred_val < 0] = 0
y_pred_train = np.round(y_pred_train_reg + y_pred_train_cas)
y_pred_train[y_pred_train < 0] = 0
y_pred_test = np.round(y_pred_test_reg + y_pred_test_cas)
y_pred_test[y_pred_test < 0] = 0
return y_pred_val, y_pred_train, y_pred_test, val_y, train_y[
'count'], test_date_df
