coal_materials/20240102.ipynb

In [1]:

import pandas as pd

In [6]:

data_0102 = pd.read_excel('./data/20240102/20240102.xlsx', header=[0,1,2])
data_0102

Out[6]:

	Unnamed: 0_level_0	氢	碳	氮	氧	弹筒发热量	挥发分	固定炭
	化验编号	Had	Cad	Nad	Oad	Qb,ad	Vad	Fcad
	Unnamed: 0_level_2	(%)	(%)	(%)	(%)	MJ/kg	(%)	(%)
0	2720110529	3.93	70.18	0.81	25.079	27.820	32.06	55.68
1	2720096883	3.78	68.93	0.77	26.512	27.404	29.96	54.71
2	2720109084	3.48	69.60	0.76	26.148	27.578	29.31	55.99
3	2720084708	3.47	66.71	0.76	29.055	26.338	28.58	53.87
4	2720062721	3.87	68.78	0.80	26.542	27.280	29.97	54.78
...	...	...	...	...	...	...	...	...
223	2720030490	4.12	68.85	0.97	26.055	27.864	32.94	51.89
224	2720028633	3.97	67.04	0.94	28.043	27.368	31.88	51.38
225	2720028634	4.12	68.42	0.96	26.493	27.886	33.16	52.00
226	2720017683	3.88	67.42	0.94	27.760	26.616	31.65	50.56
227	2720017678	3.81	66.74	0.92	28.530	26.688	31.02	50.82

228 rows × 8 columns

In [10]:

cols = [''.join([y for y in x if 'Unnamed' not in y]) for x in data_0102.columns]
cols

Out[10]:

['化验编号',
 '氢Had(%)',
 '碳Cad(%)',
 '氮Nad(%)',
 '氧Oad(%)',
 '弹筒发热量Qb,adMJ/kg',
 '挥发分Vad(%)',
 '固定炭Fcad(%)']

In [11]:

data_0102.columns = cols

In [27]:

import xgboost as xgb

In [16]:

feature_cols = cols[1:6]
feature_cols

Out[16]:

['氢Had(%)', '碳Cad(%)', '氮Nad(%)', '氧Oad(%)', '弹筒发热量Qb,adMJ/kg']

In [44]:

train_data = data_0102.copy()
train_data.head()

Out[44]:

	化验编号	氢Had(%)	碳Cad(%)	氮Nad(%)	氧Oad(%)	弹筒发热量Qb,adMJ/kg	挥发分Vad(%)	固定炭Fcad(%)
0	2720110529	3.93	70.18	0.81	25.079	27.820	32.06	55.68
1	2720096883	3.78	68.93	0.77	26.512	27.404	29.96	54.71
2	2720109084	3.48	69.60	0.76	26.148	27.578	29.31	55.99
3	2720084708	3.47	66.71	0.76	29.055	26.338	28.58	53.87
4	2720062721	3.87	68.78	0.80	26.542	27.280	29.97	54.78

In [19]:

import seaborn as sns

In [21]:

import numpy as np

In [23]:

train_data.reset_index(drop=True, inplace=True)

In [24]:

from sklearn.metrics import mean_absolute_error, mean_squared_error, mean_absolute_percentage_error, r2_score

In [40]:

param_xgb = {"silent": True,
             "obj": 'reg:linear',
             "subsample": 1,
             "max_depth": 15,
             "eta": 0.3,
             "gamma": 0,
             "lambda": 1,
             "alpha": 0,
             "colsample_bytree": 0.9,}
num_round = 1000

In [41]:

from sklearn.model_selection import KFold, train_test_split
kf = KFold(n_splits=10, shuffle=True, random_state=42)

In [43]:

eva_list = list()
for (train_index, test_index) in kf.split(train_data):
    train = train_data.loc[train_index]
    valid = train_data.loc[test_index]
    X_train, Y_train = train[feature_cols], np.log1p(train['挥发分Vad(%)'])
    X_valid, Y_valid = valid[feature_cols], np.log1p(valid['挥发分Vad(%)'])
    dtrain = xgb.DMatrix(X_train, Y_train)
    dvalid = xgb.DMatrix(X_valid, Y_valid)
    watchlist = [(dvalid, 'eval')]
    gb_model = xgb.train(params_xgb, dtrain, num_boost_round, evals=watchlist,
                    early_stopping_rounds=50, verbose_eval=False)
    y_pred = np.expm1(gb_model.predict(xgb.DMatrix(X_valid)))
    y_true = np.expm1(Y_valid.values)
    MSE = mean_squared_error(y_true, y_pred)
    RMSE = np.sqrt(mean_squared_error(y_true, y_pred))
    MAE = mean_absolute_error(y_true, y_pred)
    MAPE = mean_absolute_percentage_error(y_true, y_pred)
    R_2 = r2_score(y_true, y_pred)
    print('MSE:', round(MSE, 4), end=', ')
    print('RMSE:', round(RMSE, 4), end=', ')
    print('MAE:', round(MAE, 4), end=', ')
    print('MAPE:', round(MAPE*100, 2), '%', end=', ')
    print('R_2:', round(R_2, 4))  #R方为负就说明拟合效果比平均值差
    eva_list.append([MSE, RMSE, MAE, MAPE, R_2])
data_df = pd.DataFrame.from_records(eva_list, columns=['MSE', 'RMSE', 'MAE', 'MAPE', 'R_2'])
data_df.mean()

MSE: 1.9436, RMSE: 1.3941, MAE: 1.1861, MAPE: 3.94 %, R_2: 0.6095
MSE: 1.8735, RMSE: 1.3688, MAE: 1.132, MAPE: 3.77 %, R_2: 0.495
MSE: 2.0587, RMSE: 1.4348, MAE: 1.0706, MAPE: 4.08 %, R_2: 0.7862
MSE: 1.9298, RMSE: 1.3892, MAE: 1.1469, MAPE: 3.84 %, R_2: 0.5332
MSE: 1.4583, RMSE: 1.2076, MAE: 1.097, MAPE: 3.67 %, R_2: 0.6894
MSE: 2.0822, RMSE: 1.443, MAE: 1.1645, MAPE: 3.88 %, R_2: 0.5975
MSE: 1.3521, RMSE: 1.1628, MAE: 0.9905, MAPE: 3.37 %, R_2: 0.7479
MSE: 1.4057, RMSE: 1.1856, MAE: 0.9998, MAPE: 3.3 %, R_2: 0.2946
MSE: 2.2274, RMSE: 1.4925, MAE: 1.2638, MAPE: 4.19 %, R_2: 0.6785
MSE: 1.4866, RMSE: 1.2193, MAE: 1.0797, MAPE: 3.67 %, R_2: 0.7261

Out[43]:

MSE     1.781792
RMSE    1.329760
MAE     1.113084
MAPE    0.037719
R_2     0.615796
dtype: float64

In [48]:

eva_list = list()
for (train_index, test_index) in kf.split(train_data):
    train = train_data.loc[train_index]
    valid = train_data.loc[test_index]
    X_train, Y_train = train[feature_cols], np.log1p(train['固定炭Fcad(%)'])
    X_valid, Y_valid = valid[feature_cols], np.log1p(valid['固定炭Fcad(%)'])
    dtrain = xgb.DMatrix(X_train, Y_train)
    dvalid = xgb.DMatrix(X_valid, Y_valid)
    watchlist = [(dvalid, 'eval')]
    gb_model = xgb.train(params_xgb, dtrain, num_boost_round, evals=watchlist,
                    early_stopping_rounds=50, verbose_eval=False)
    y_pred = np.expm1(gb_model.predict(xgb.DMatrix(X_valid)))
    y_true = np.expm1(Y_valid.values)
    MSE = mean_squared_error(y_true, y_pred)
    RMSE = np.sqrt(mean_squared_error(y_true, y_pred))
    MAE = mean_absolute_error(y_true, y_pred)
    MAPE = mean_absolute_percentage_error(y_true, y_pred)
    R_2 = r2_score(y_true, y_pred)
    print('MSE:', round(MSE, 4), end=', ')
    print('RMSE:', round(RMSE, 4), end=', ')
    print('MAE:', round(MAE, 4), end=', ')
    print('MAPE:', round(MAPE*100, 2), '%', end=', ')
    print('R2:', round(R_2, 4))  #R方为负就说明拟合效果比平均值差
    eva_list.append([MSE, RMSE, MAE, MAPE, R_2])
data_df = pd.DataFrame.from_records(eva_list, columns=['MSE', 'RMSE', 'MAE', 'MAPE', 'R2'])
data_df.mean()

MSE: 4.6724, RMSE: 2.1616, MAE: 1.7297, MAPE: 3.42 %, R2: 0.8346
MSE: 3.0512, RMSE: 1.7468, MAE: 1.4485, MAPE: 2.62 %, R2: 0.8011
MSE: 7.6672, RMSE: 2.769, MAE: 1.951, MAPE: 4.56 %, R2: 0.8856
MSE: 4.0334, RMSE: 2.0083, MAE: 1.487, MAPE: 2.77 %, R2: 0.8216
MSE: 2.6382, RMSE: 1.6243, MAE: 1.1551, MAPE: 2.12 %, R2: 0.846
MSE: 5.8097, RMSE: 2.4103, MAE: 1.8683, MAPE: 3.8 %, R2: 0.83
MSE: 2.3446, RMSE: 1.5312, MAE: 1.1294, MAPE: 2.28 %, R2: 0.9069
MSE: 3.0069, RMSE: 1.734, MAE: 1.3782, MAPE: 2.46 %, R2: 0.6541
MSE: 4.1652, RMSE: 2.0409, MAE: 1.5685, MAPE: 3.2 %, R2: 0.859
MSE: 4.2023, RMSE: 2.05, MAE: 1.6284, MAPE: 3.2 %, R2: 0.869

Out[48]:

MSE     4.159107
RMSE    2.007631
MAE     1.534427
MAPE    0.030424
R2      0.830794
dtype: float64

In [67]:

Out[67]:

	MSE	RMSE	MAE	MAPE	R2
十折交叉验证均值	4.159107	2.007631	1.534427	0.030424	0.830794

In [ ]: