def choose_xgb_config:
#xgboost
_tmp_config = {
'acc' : 0,
'dep' : None,
'est' : None
}
for depth_ in [4,6,8,10,12,16,20,32,64]:
for est in [100,200,300,500,700,1000,1200,1400,1500]:
model = xgbr(max_depth=depth_,
n_estimators=est,
eval_metric='rmse',
n_jobs=4,
learning_rate=0.18
)
model.fit(X_train, Y_train)
accuracy = model.score(X_test, Y_test)
if accuracy > _tmp_config['acc']:
_tmp_config['acc'], _tmp_config['dep'], _tmp_config['est'] = (accuracy, depth_, est)
print("Accuracy: {}, dep: {}, est: {}".format(accuracy * 100.0, depth_, est))
return _tmp_config
X_test.head()
#%%
# Make a CSV backup of our test data without column names or indexes
test_data = X_test.copy()
test_data['target'] = y_test
test_data.to_csv("test_data.csv", header=False, index=False)
#%%
test_data.head()
#%%
model = xgbr()
model.fit(X_train, y_train, eval_set=[(X_test, y_test)])
#%%
conv_model = convert_xgboost(model, initial_types=[('float_input', FloatTensorType(shape=[1, 4]))])
assert(conv_model is not None)
save_model(conv_model, 'model.onnx')
#%%
def main():
# random number initialization
np.random.seed(123456000)
# preprocess data by PCA and standardization
Xtrain__full, ytrain__full, Xtest = load_data(argv[1], argv[2])
# Xtrain__full, ytrain__full, Xtest = load_data("train_data.csv","test_data.csv")
Xtrain__full, ytrain__full, Xtest = preprocess(Xtrain__full, ytrain__full,
Xtest)
# train-set and validation-set split
X_train, X_val, y_train, y_val = train_test_split(Xtrain__full,
ytrain__full,
test_size=0.20,
random_state=None)
# ============================================================================================================
print(" ")
print(" ")
print("Linear regressor classifier")
start_time = time.time()
LR = regressor(0.01)
LR.fit(X_train, y_train)
show_performance(LR, X_train, y_train, "Train")
show_performance(LR, X_val, y_val, "Validation")
show_time(time.time() - start_time)
# ============================================================================================================
print("Stochastic gradient descent regressor classifier")
start_time = time.time()
SGDR = SGDRegressor(loss='huber',
penalty='elasticnet',
max_iter=100,
eta0=0.01)
SGDR.fit(X_train, y_train.flatten())
show_performance(SGDR, X_train, y_train, "Train")
show_performance(SGDR, X_val, y_val, "Validation")
show_time(time.time() - start_time)
# ============================================================================================================
print("Neural network classifier")
start_time = time.time()
def baseline_model(D):
# Defining the NN based regressor
model = Sequential()
model.add(
Dense(D,
input_dim=D,
kernel_initializer='glorot_uniform',
activation='relu'))
model.add(Dropout(0.25))
model.add(
Dense(D,
input_dim=D,
kernel_initializer='glorot_uniform',
activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(1, kernel_initializer='glorot_uniform'))
model.compile(loss='mae', optimizer='adam', metrics=['mae'])
return model
_, D = np.shape(X_train)
# KR = KerasRegressor(build_fn=baseline_model(D), epochs=30, batch_size=16, verbose=False)
KR = baseline_model(D)
KR.fit(X_train, y_train, epochs=100, batch_size=16, verbose=False)
show_performance(KR, X_train, y_train, "Train")
show_performance(KR, X_val, y_val, "Validation")
show_time(time.time() - start_time)
# ============================================================================================================
print("Extratrees regressor classifier")
start_time = time.time()
ET = ExtraTreesRegressor(n_estimators=200,
criterion='mae',
min_samples_split=2,
min_samples_leaf=1)
ET.fit(X_train, y_train.flatten())
show_performance(ET, X_train, y_train, "Train")
show_performance(ET, X_val, y_val, "Validation")
show_time(time.time() - start_time)
# ============================================================================================================
print("Extreme gradient boosted regressor classifier")
start_time = time.time()
n = Xtrain__full.shape[1]
XGBR = xgbr(n_estimators=400, max_depth=int(np.sqrt(n)))
XGBR.fit(X_train, y_train.flatten())
show_performance(XGBR, X_train, y_train, "Train")
show_performance(XGBR, X_val, y_val, "Validation")
show_time(time.time() - start_time)
# ============================================================================================================
print("Soft voting over best performing ET and XGBR classifiers")
temp1 = ET.predict(X_val)
temp2 = XGBR.predict(X_val)
temp = np.average([temp1, temp2], axis=0, weights=[7, 10])
mae = mean_absolute_error(y_val, temp)
print("Validation MAE: %f" % mae)
# ============================================================================================================
print(" ")
print(" ")
print("Writing out the results")
temp1 = ET.predict(Xtest)
temp2 = XGBR.predict(Xtest)
temp = np.average([temp1, temp2], axis=0, weights=[7, 10])
predictions = temp.astype(int)
df = pd.read_csv(argv[2])
# df = pd.read_csv("test_data.csv")
df['predicted_ground_truth'] = predictions
df.to_csv(argv[2], index=False)
# df.to_csv('test_data.csv', index=False)
print("Task completed")
model_3.add(Dropout(0.2))
model_3.add(Flatten())
model_3.add(Dense(1024, activation='relu'))
model_3.add(Dense(512, activation='relu'))
model_3.add(Dropout(0.3))
model_3.add(Dense(1, activation='linear'))
model_3.compile(loss="mse",
optimizer="adam",
metrics=["accuracy", "mse"])
print(model_3.summary())
history_3 = model_3.fit(
X_train, y_train,
batch_size = 16,
epochs = 2000
)
model = xgbr(max_depth = 8,
n_estimators = 118,
eval_metric = 'rmse',
n_jobs = 4,
learning_rate = 0.2
)
model.fit(X_train, Y_train)
accuracy = model.score(X_test, Y_test)
print("Accuracy: %.4f%%" % (accuracy * 100.0))
plt.rcParams['figure.figsize'] = (30, 30)
xgboost.plot_tree(model, num_trees=1)
plt.show()
from sklearn.linear_model import LinearRegression as linear from sklearn.model_selection import KFold, cross_val_score as cvs, train_test_split as tts from sklearn.metrics import mean_squared_error as mse from sklearn.datasets import load_boston import pandas as pd import numpy as np import matplotlib.pyplot as plt from time import time import datetime data = load_boston() x = data.data y = data.target xtrain, xtest, ytrain, ytest = tts(x, y, test_size=0.3, random_state=420) reg = xgbr(n_setimators=100).fit(xtrain, ytrain) #预测值&score reg.predict(xtest) reg.score(xtest, ytest) # 均方误差和均值 mse(ytest, reg.predict(xtest)) y.mean() #特征的重要性 reg.feature_importances_ #3.以下用交叉验证来对比,xgbr 随机森林，线性回归 reg = xgbr(n_eatimators=100) cvs(reg, xtrain, ytrain, cv=5).mean() # 交叉验证 cvs(reg, xtrain, ytrain, cv=5, scoring='neg_mean_squared_error').mean() rfr = rfr(n_estimators=100)
# grid_search.fit(train_data, price)
# evalute_result = grid_search.cv_results_
# print('每轮的迭代结果:{}'.format(evalute_result))
# print('best_params:', grid_search.best_params_)
# print('best_score:', grid_search.best_score_)
# print('GridSearchCV process use %.2f seconds'%(time.time()-start))
# 模型定义
print('xgb模型训练中...')
model_xgb = xgbr(learning_rate=0.1, # 0.1, default=0.3
n_estimators=1000, # 1000
max_depth=10, # 10, default=6
min_child_weight=2, # 2, default=1
subsample=0.8, # 0.8, default=1
colsample_bytree=0.9, # 0.9, default=1
gamma=0.7, # 0.7, default=0
reg_alpha=0, # 0, default=0
reg_lambda=0.1, # 0.1, default=1
n_jobs=8)
model_xgb.fit(train_data, price)
y_pred_xgb = model_xgb.predict(test_data)
# y_pred_xgb = np.round(np.exp(y_pred_xgb), 0)
print('lgb模型训练中...')
model_lgb = lgb.LGBMRegressor(n_estimators=500, learning_rate=0.1, n_jobs=8)
model_lgb.fit(train_data, price)
y_pred_lgb = model_lgb.predict(test_data)
# y_pred_lgb = np.round(np.exp(y_pred_lgb), 0)
print('gbdt模型训练中...')