def q07_randomforest_regressor(path,columns = fe, random_state =9):
np.random.seed(random_state)
data = q05_feature_engineering_part4(path)
splits = q02_data_splitter(path)
rmse = []
for i in splits:
train = i[0]
valid = i[1]
x_train, y_train = data[fe].values[train], data['Demand'].values[train]
x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid]
model = RandomForestRegressor( n_estimators=50, min_samples_leaf=30, random_state=10)
model.fit(x_train, y_train)
pred = model.predict(x_valid)
measure = math.pow(mean_squared_error(y_valid, pred), 0.5)
rmse.append(measure)
return np.mean(rmse)
def q06_linear_regression(path, columns=fe, random_state=9):
np.random.seed(random_state)
data = q05_feature_engineering_part4(path)
com_idx = q02_data_splitter(path)
rmse = []
for i in com_idx:
train_idx = i[0]
valid_idx = i[1]
X_train, y_train = data.ix[train_idx, fe], data.ix[train_idx, 'Demand']
X_valid, y_valid = data.ix[valid_idx, fe], data.ix[valid_idx, 'Demand']
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_valid)
rms = mean_squared_error(y_valid, y_pred)**0.5
rmse.append(rms)
return np.mean(rmse)
def q06_linear_regression(path, columns=fe, random_state=9):
np.random.seed(random_state)
data = q05_feature_engineering_part4(path)
splits = q02_data_splitter(path)
rmse = []
for i in splits:
train = i[0]
valid = i[1]
x_train, y_train = data[fe].values[train], data['Demand'].values[train]
x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid]
model = LinearRegression()
model.fit(x_train, y_train)
pred = model.predict(x_valid)
measure = math.pow(mean_squared_error(y_valid, pred), 0.5)
rmse.append(measure)
return np.mean(rmse)
def q07_randomforest_regressor(path, columns=fe, random_state=9):
np.random.seed(random_state)
data = q05_feature_engineering_part4(path)
com_idx = q02_data_splitter(path)
rmse = []
for i in com_idx:
train_idx = i[0]
valid_idx = i[1]
X_train, y_train = data.ix[train_idx, fe], data.ix[train_idx, 'Demand']
X_valid, y_valid = data.ix[valid_idx, fe], data.ix[valid_idx, 'Demand']
model = RandomForestRegressor(n_estimators=50,
min_samples_leaf=30,
random_state=10)
model.fit(X_train, y_train)
y_pred = model.predict(X_valid)
rms = mean_squared_error(y_valid, y_pred)**0.5
rmse.append(rms)
return np.mean(rmse)
def q08_gradientboosting_regressor(path,columns = fe, random_state =9):
np.random.seed(random_state)
data = q05_feature_engineering_part4(path)
splits = q02_data_splitter(path)
'write your solution here'
rmse = []
for i in splits:
train = i[0]
valid = i[1]
x_train, y_train = data[fe].values[train], data['Demand'].values[train]
x_valid, y_valid = data[fe].values[valid], data['Demand'].values[valid]
model = GradientBoostingRegressor(n_estimators=200, min_samples_leaf=10, learning_rate=0.01, random_state=random_state)
model.fit(x_train, y_train)
pred = model.predict(x_valid)
measure = math.pow(mean_squared_error(y_valid, pred), 0.5)
rmse.append(measure)
return np.mean(rmse)
