<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10886 entries, 0 to 10885
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 datetime 10886 non-null object
1 season 10886 non-null int64
2 holiday 10886 non-null int64
3 workingday 10886 non-null int64
4 weather 10886 non-null int64
5 temp 10886 non-null float64
6 atemp 10886 non-null float64
7 humidity 10886 non-null int64
8 windspeed 10886 non-null float64
9 casual 10886 non-null int64
10 registered 10886 non-null int64
11 count 10886 non-null int64
dtypes: float64(3), int64(8), object(1)
memory usage: 1020.7+ KB
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10886 entries, 0 to 10885
Data columns (total 16 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 datetime 10886 non-null datetime64[ns]
1 season 10886 non-null int64
2 holiday 10886 non-null int64
3 workingday 10886 non-null int64
4 weather 10886 non-null int64
5 temp 10886 non-null float64
6 atemp 10886 non-null float64
7 humidity 10886 non-null int64
8 windspeed 10886 non-null float64
9 casual 10886 non-null int64
10 registered 10886 non-null int64
11 count 10886 non-null int64
12 year 10886 non-null int64
13 month 10886 non-null int64
14 day 10886 non-null int64
15 hour 10886 non-null int64
dtypes: datetime64[ns](1), float64(3), int64(12)
memory usage: 1.3 MB
fig, axs = plt.subplots(figsize=(16, 8), ncols=4, nrows=2)
cat_features = ['year', 'month','season','weather','day', 'hour', 'holiday','workingday']
# cat_features에 있는 모든 칼럼별로 개별 칼럼값에 따른 count의 합을 barplot으로 시각화
for i, feature in enumerate(cat_features):
row = int(i/4)
col = i%4
# 시본의 barplot을 이용해 칼럼값에 따른 count의 평균값을 표현
sns.barplot(x=feature, y='count', data=bike_df, ax=axs[row][col])
from sklearn.metrics import mean_squared_error, mean_absolute_error
# log 값 변환 시 NaN등의 이슈로 log() 가 아닌 log1p() 를 이용하여 RMSLE 계산
def rmsle(y, pred):
log_y = np.log1p(y)
log_pred = np.log1p(pred)
squared_error = (log_y - log_pred) ** 2
rmsle = np.sqrt(np.mean(squared_error))
return rmsle
# 사이킷런의 mean_square_error() 를 이용하여 RMSE 계산
def rmse(y,pred):
return np.sqrt(mean_squared_error(y,pred))
# MSE, RMSE, RMSLE 를 모두 계산
def evaluate_regr(y,pred):
rmsle_val = rmsle(y,pred)
rmse_val = rmse(y,pred)
# MAE 는 scikit learn의 mean_absolute_error() 로 계산
mae_val = mean_absolute_error(y,pred)
print('RMSLE: {0:.3f}, RMSE: {1:.3F}, MAE: {2:.3F}'.format(rmsle_val, rmse_val, mae_val))
4.61512051684126 100.00000000000003
from sklearn.model_selection import train_test_split , GridSearchCV
from sklearn.linear_model import LinearRegression , Ridge , Lasso
y_target = bike_df['count']
X_features = bike_df.drop(['count'],axis=1,inplace=False)
X_train, X_test, y_train, y_test = train_test_split(X_features, y_target, test_size=0.3, random_state=0)
lr_reg = LinearRegression()
lr_reg.fit(X_train, y_train)
pred = lr_reg.predict(X_test)
evaluate_regr(y_test ,pred)
RMSLE: 1.165, RMSE: 140.900, MAE: 105.924
def get_top_error_data(y_test, pred, n_tops = 5):
# DataFrame에 컬럼들로 실제 대여횟수(count)와 예측 값을 서로 비교 할 수 있도록 생성.
result_df = pd.DataFrame(y_test.values, columns=['real_count'])
result_df['predicted_count']= np.round(pred)
result_df['diff'] = np.abs(result_df['real_count'] - result_df['predicted_count'])
# 예측값과 실제값이 가장 큰 데이터 순으로 출력.
print(result_df.sort_values('diff', ascending=False)[:n_tops])
get_top_error_data(y_test,pred,n_tops=5)
real_count predicted_count diff
1618 890 322.0 568.0
3151 798 241.0 557.0
966 884 327.0 557.0
412 745 194.0 551.0
2817 856 310.0 546.0
# 타깃 칼럼인 count 값을 log1p로 로그 변환
y_target_log = np.log1p(y_target)
# 로그 변환된 y_target_log를 반영하여 학습/테스트 데이터 셋 분할
X_train, X_test, y_train, y_test = train_test_split(X_features, y_target_log, test_size=0.3, random_state=0)
lr_reg = LinearRegression()
lr_reg.fit(X_train, y_train)
pred = lr_reg.predict(X_test)
# 테스트 데이터 셋의 Target 값은 Log 변환되었으므로 다시 expm1를 이용하여 원래 scale로 변환
y_test_exp = np.expm1(y_test)
# 예측 값 역시 Log 변환된 타깃 기반으로 학습되어 예측되었으므로 다시 exmpl으로 scale변환
pred_exp = np.expm1(pred)
evaluate_regr(y_test_exp ,pred_exp)
RMSLE: 1.017, RMSE: 162.594, MAE: 109.286
array([308.63045453, 161.17120235, 146.5153226 , ..., 351.91134842,
153.35179351, 74.17859374])
year 0.418513
hour 0.098348
month 0.076839
atemp 0.030857
temp 0.011712
windspeed 0.003961
day 0.003353
humidity -0.014512
weather -0.014733
season -0.044525
holiday -0.046010
workingday -0.066383
dtype: float64
# 'year', month', 'day', hour'등의 피처들을 One Hot Encoding
X_features_ohe = pd.get_dummies(X_features, columns=['year', 'month','day', 'hour', 'holiday',
'workingday','season','weather'])
# 원-핫 인코딩이 적용된 feature 데이터 세트 기반으로 학습/예측 데이터 분할.
X_train, X_test, y_train, y_test = train_test_split(X_features_ohe, y_target_log,
test_size=0.3, random_state=0)
# 모델과 학습/테스트 데이터 셋을 입력하면 성능 평가 수치를 반환
def get_model_predict(model, X_train, X_test, y_train, y_test, is_expm1=False):
model.fit(X_train, y_train)
pred = model.predict(X_test)
if is_expm1 :
y_test = np.expm1(y_test)
pred = np.expm1(pred)
print('###',model.__class__.__name__,'###')
evaluate_regr(y_test, pred)
# end of function get_model_predict
# model 별로 평가 수행
lr_reg = LinearRegression()
ridge_reg = Ridge(alpha=10)
lasso_reg = Lasso(alpha=0.01)
for model in [lr_reg, ridge_reg, lasso_reg]:
get_model_predict(model,X_train, X_test, y_train, y_test,is_expm1=True)
### LinearRegression ###
RMSLE: 0.590, RMSE: 97.688, MAE: 63.382
### Ridge ###
RMSLE: 0.590, RMSE: 98.529, MAE: 63.893
### Lasso ###
RMSLE: 0.635, RMSE: 113.219, MAE: 72.803
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
# 랜덤 포레스트, GBM, XGBoost, LightGBM model 별로 평가 수행
rf_reg = RandomForestRegressor(n_estimators=500)
gbm_reg = GradientBoostingRegressor(n_estimators=500)
xgb_reg = XGBRegressor(n_estimators=500)
lgbm_reg = LGBMRegressor(n_estimators=500)
for model in [rf_reg, gbm_reg, xgb_reg, lgbm_reg]:
# XGBoost의 경우 DataFrame이 입력 될 경우 버전에 따라 오류 발생 가능. ndarray로 변환.
get_model_predict(model,X_train.values, X_test.values, y_train.values, y_test.values,is_expm1=True)
### RandomForestRegressor ###
RMSLE: 0.355, RMSE: 50.442, MAE: 31.170
### GradientBoostingRegressor ###
RMSLE: 0.330, RMSE: 53.315, MAE: 32.730
### XGBRegressor ###
RMSLE: 0.342, RMSE: 51.732, MAE: 31.251
### LGBMRegressor ###
RMSLE: 0.319, RMSE: 47.215, MAE: 29.029
