import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import metrics
import pickle
from xgboost.sklearn import XGBRegressor
from sklearn.preprocessing import StandardScaler
from clean_data import prep_water_data, normalize_water_data, normalize_data, delete_null_date
from sklearn.model_selection import KFold, train_test_split, GridSearchCV, cross_val_score
from sklearn.model_selection import TimeSeriesSplit
def GDBTTrain(X, y):
"""xgboost用法"""
train_x, test_x, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=0) ##test_size测试集合所占比例
test_preds = pd.DataFrame({"label": test_y})
clf = XGBRegressor(
learning_rate=0.1, # 默认0.3
n_estimators=400, # 树的个数
max_depth=8,
)
clf.fit(train_x, train_y)
test_preds['y_pred'] = clf.predict(test_x)
stdm = metrics.r2_score(test_preds['label'], test_preds['y_pred'])
# GridSearchCV和cross_val_score的结果一样
# scores = cross_val_score(clf, X, y, scoring='r2')
# print(scores)
# gs = GridSearchCV(clf, {}, cv=3, verbose=3).fit(X, y)
return stdm, clf
def XGTSearch(X, y):
print("Parameter optimization")
n_estimators = [50, 100, 200, 400]
max_depth = [2, 4, 6, 8]
learning_rate = [0.0001, 0.001, 0.01, 0.1, 0.2, 0.3]
param_grid = dict(max_depth=max_depth, n_estimators=n_estimators, learning_rate=learning_rate)
xgb_model = XGBRegressor()
kfold = TimeSeriesSplit(n_splits=2).get_n_splits([X, y])
fit_params = {"eval_metric": "rmse"}
grid_search = GridSearchCV(xgb_model, param_grid, verbose=1, fit_params=fit_params, cv=kfold)
grid_result = grid_search.fit(X, y)
# summarize results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
return means, grid_result
feature_string = 'EnterCOD EnterBOD EnterAD EnterZL EnterZD EnterPH EnterSS M4 N4 O4 P4 Q4 R4' # 选取的特征
outputs_string = 'mlss mlvss sv30 OutCOD OutBOD OutAD OutZL OutZD OutPH OutSS' # 需要预测的标签
feature = feature_string.split()
outputs = outputs_string.split()
print(feature)
['EnterCOD', 'EnterBOD', 'EnterAD', 'EnterZL', 'EnterZD', 'EnterPH', 'EnterSS', 'M4', 'N4', 'O4', 'P4', 'Q4', 'R4']
def prep_water_data(data, columns):
for c in columns:
data[c] = [0 if ((x in ['Not Available', 'Not Mapped', 'NULL']) | (pd.isnull(x))) else x for x in data[c]]
return data
def delete_null_date(data, date_name):
data = data[data[date_name].notnull()] # 删除日期存在缺失的数据
return data
data = pd.read_csv('water_a.csv', encoding="gb18030")
data = prep_water_data(data, feature)
print(data.iloc[:5][feature])
EnterCOD EnterBOD EnterAD EnterZL EnterZD EnterPH EnterSS M4 \
0 299.0 0.0 16.7 9.63 26.5 7 354.0 4609.0
1 331.0 0.0 15.0 9.34 31.8 7 297.5 4834.0
2 326.0 0.0 19.6 11.17 33.5 7 389.5 4928.0
3 230.0 0.0 17.4 6.23 32.3 7 277.5 5073.0
4 149.0 0.0 16.8 3.59 23.7 7 106.0 4856.0
N4 O4 P4 Q4 R4
0 2346.0 1.72 32.0 69.43 17.0
1 2434.0 1.72 34.0 70.34 18.0
2 2604.0 1.70 35.0 71.02 18.0
3 2678.0 1.68 36.0 70.96 19.0
4 2452.0 1.69 37.0 76.19 19.0
def predict(data, out):
data = delete_null_date(data, out)
y = data[out]
# y = y.as_matrix()
X = data[feature]
stdm, clf = GDBTTrain(X, y)
print(out +'准确率：', stdm)
feature_importance = clf.feature_importances_
feature_importance = 100.0 * (feature_importance / feature_importance.max())
print('特征：', X.columns)
print('每个特征的重要性：', feature_importance)
sorted_idx = np.argsort(feature_importance)
pos = np.arange(sorted_idx.shape[0])
plt.barh(pos, feature_importance[sorted_idx], align='center')
plt.yticks(pos, X.columns[sorted_idx])
plt.xlabel('Features')
plt.ylabel('Importance')
plt.title('Variable Importance')
plt.show()
#.......................选取重要性高的特征再次进行训练和预测..................................#
X = data[X.columns[sorted_idx][::-1][:-1]]
stdm, clf = GDBTTrain(X, y)
print(out +'选取重要特征后准确率：', stdm)
feature_importance = clf.feature_importances_
feature_importance = 100.0 * (feature_importance / feature_importance.max())
print('重要特征：', X.columns)
print('每个重要特征的重要性：', feature_importance)
sorted_idx = np.argsort(feature_importance)
pos = np.arange(sorted_idx.shape[0])
plt.barh(pos, feature_importance[sorted_idx], align='center')
plt.yticks(pos, X.columns[sorted_idx])
plt.xlabel('Features')
plt.ylabel('Importance')
plt.title('重要特征 Variable Importance')
plt.show()
for out in outputs[:1]:
sorted_idx = predict(data, out)
mlss准确率： 0.950752699205583
特征： Index(['EnterCOD', 'EnterBOD', 'EnterAD', 'EnterZL', 'EnterZD', 'EnterPH',
'EnterSS', 'M4', 'N4', 'O4', 'P4', 'Q4', 'R4'],
dtype='object')
每个特征的重要性： [100. 21.307432 48.90534 37.218624 26.950356 2.081406
31.82239 72.88005 49.49121 61.9334 19.071848 33.441257
17.745914]
output_10_1.png
mlss选取重要特征后准确率： 0.9485146037853682
重要特征： Index(['EnterCOD', 'M4', 'O4', 'N4', 'EnterAD', 'EnterZL', 'Q4', 'EnterSS',
'EnterZD', 'EnterBOD', 'P4', 'R4'],
dtype='object')
每个重要特征的重要性： [100. 92.00673 75.79092 55.387436 36.038513 32.217636
42.442307 28.243927 24.789852 12.685312 18.707016 19.150238]
output_10_3.png