def main():
"""
主函数
"""
# 准备数据集
train_data, test_data = utils.prepare_data()
# 查看数据集
utils.inspect_dataset(train_data, test_data)
# 特征工程处理
# 构建训练测试数据
X_train, X_test = utils.do_feature_engineering(train_data, test_data)
print('共有{}维特征。'.format(X_train.shape[1]))
# 标签处理
y_train = train_data['label'].values
y_test = test_data['label'].values
# 数据建模及验证
print('\n===================== 数据建模及验证 =====================')
nb_model = GaussianNB()
nb_model.fit(X_train, y_train)
y_pred = nb_model.predict(X_test)
print('准确率：', accuracy_score(y_test, y_pred))
print('AUC值：', roc_auc_score(y_test, y_pred))
def main():
"""
主函数
"""
# 加载数据
raw_data = pd.read_csv(os.path.join(config.dataset_path,
'charging_pile.csv'),
index_col='id')
# 分割数据集
train_data, test_data = train_test_split(raw_data,
test_size=1 / 4,
random_state=10)
# 数据查看
utils.inspect_dataset(train_data, test_data)
# 特征工程
print('\n===================== 特征工程 =====================')
X_train, y_train = utils.transform_data(train_data)
X_test, y_test = utils.transform_data(test_data)
# 构建训练测试数据
# 数据建模及验证
print('\n===================== 数据建模及验证 =====================')
model_name_param_dict = {'kNN': [5, 11, 15], 'LR': [0.1, 1, 10]}
# 比较结果的DataFrame
results_df = pd.DataFrame(columns=['Accuracy (%)', 'Time (s)'],
index=list(model_name_param_dict.keys()))
results_df.index.name = 'Model'
for model_name, param_range in model_name_param_dict.items():
_, best_acc, mean_duration = utils.train_test_model(
X_train, y_train, X_test, y_test, param_range, model_name)
results_df.loc[model_name, 'Accuracy (%)'] = best_acc * 100
results_df.loc[model_name, 'Time (s)'] = mean_duration
results_df.to_csv(os.path.join(config.output_path, 'model_comparison.csv'))
# 模型及结果比较
print('\n===================== 模型及结果比较 =====================')
plt.figure(figsize=(10, 4))
ax1 = plt.subplot(1, 2, 1)
results_df.plot(y=['Accuracy (%)'],
kind='bar',
ylim=[60, 100],
ax=ax1,
title='Accuracy(%)',
legend=False)
ax2 = plt.subplot(1, 2, 2)
results_df.plot(y=['Time (s)'],
kind='bar',
ax=ax2,
title='Time(s)',
legend=False)
plt.tight_layout()
plt.savefig(os.path.join(config.output_path, 'pred_results.png'))
plt.show()
def main():
"""
主函数
"""
# 准备数据集
train_data, test_data = utils.prepare_data()
# 查看数据集
utils.inspect_dataset(train_data, test_data)
# 特征工程处理
# 构建训练测试数据
X_train, X_test = utils.do_feature_engineering(train_data, test_data)
print('共有{}维特征。'.format(X_train.shape[1]))
# 标签处理
y_train = train_data['label'].values
y_test = test_data['label'].values
# 数据建模及验证
print('\n===================== 数据建模及验证 =====================')
nb_model = GaussianNB()
nb_model.fit(X_train, y_train)
y_pred = nb_model.predict(X_test)
print('准确率：', accuracy_score(y_test, y_pred))
print('AUC值：', roc_auc_score(y_test, y_pred))
def main():
# Loading Data
cleaned = pd.read_csv(os.path.join(config.dataset_path, 'cleaned.csv'))
cleaned = cleaned[config.feat_cols]
raw_data = cleaned[pd.isna(cleaned.y)==False]
valid = cleaned[pd.isna(cleaned.y)]
# Cleaning Data
# Splitting Data
train_data, test_data = train_test_split(raw_data, test_size=1/4, random_state=10)
y_train = train_data['y'].values
y_test = test_data['y'].values
train_data = train_data.drop('y', axis=1)
test_data = test_data.drop('y', axis=1)
# Checking Data
utils.inspect_dataset(train_data, test_data)
# Feature Engineering
print('\n===================== Feature Engineering =====================')
X_train, label_encs, onehot_enc, scaler, pca = utils.transform_train_data(train_data)
X_test = utils.transform_test_data(test_data, label_encs, onehot_enc, scaler, pca)
X_valid = utils.transform_test_data(valid, label_encs, onehot_enc, scaler, pca)
# Testing
print('\n===================== Modeling =====================')
model_name_param_dict = {'LR': LinearRegression(),
'Lasso': Lasso(alpha=0.01),
'Ridge': Ridge(alpha=0.01),
'SVM':SVR(),
'SGD':SGDRegressor()
}
# Create tables
results_df = pd.DataFrame(columns=['MSE', 'Time (s)'],
index=list(model_name_param_dict.keys()))
results_df.index.name = 'Model'
for model_name, model in model_name_param_dict.items():
_, best_score, mean_duration = utils.train_test_model(X_train, y_train, X_test, y_test, model_name, model)
results_df.loc[model_name, 'MSE'] = best_score
results_df.loc[model_name, 'Time (s)'] = mean_duration
results_df.to_csv(os.path.join(config.output_path, 'table.csv'))
lasso = Ridge(alpha=0.01)
lasso.fit(X_train, y_train)
predict = np.exp(lasso.predict(X_valid))
result = pd.DataFrame(predict)
result.to_csv('C:\\Users\\alexliuyi\\Documents\\Kaggle\\Home Price\\result.csv')
def main():
"""
主函数
"""
# 加载数据
raw_data = pd.read_csv(
os.path.join(config.dataset_path, 'german_credit_data.csv'))
# 清洗数据
cln_data = utils.clean_data(raw_data)
# 分割数据集
train_data, test_data = train_test_split(cln_data,
test_size=1 / 4,
random_state=10)
y_train = train_data['Label'].values
y_test = test_data['Label'].values
# 数据查看
utils.inspect_dataset(train_data, test_data)
# 特征工程
print('\n===================== 特征工程 =====================')
X_train, label_encs, onehot_enc, scaler, pca = utils.transform_train_data(
train_data)
X_test = utils.transform_test_data(test_data, label_encs, onehot_enc,
scaler, pca)
# 构建训练测试数据
# 数据建模及验证
print('\n===================== 数据建模及验证 =====================')
sclf = StackingClassifier(
classifiers=[KNeighborsClassifier(),
SVC(),
DecisionTreeClassifier()],
meta_classifier=LogisticRegression())
model_name_param_dict = {
'kNN': (KNeighborsClassifier(), {
'n_neighbors': [5, 25, 55]
}),
'LR': (LogisticRegression(), {
'C': [0.01, 1, 100]
}),
'SVM': (SVC(probability=True), {
'C': [0.01, 1, 100]
}),
'DT': (DecisionTreeClassifier(), {
'max_depth': [50, 100, 150]
}),
'Stacking': (sclf, {
'kneighborsclassifier__n_neighbors': [5, 25, 55],
'svc__C': [0.01, 1, 100],
'decisiontreeclassifier__max_depth': [50, 100, 150],
'meta-logisticregression__C': [0.01, 1, 100]
}),
'AdaBoost': (AdaBoostClassifier(), {
'n_estimators': [50, 100, 150, 200]
}),
'GBDT': (GradientBoostingClassifier(), {
'learning_rate': [0.01, 0.1, 1, 10, 100]
}),
'RF': (RandomForestClassifier(), {
'n_estimators': [100, 150, 200, 250]
})
}
# 比较结果的DataFrame
results_df = pd.DataFrame(columns=['AUC', 'Time (s)'],
index=list(model_name_param_dict.keys()))
results_df.index.name = 'Model'
for model_name, (model, param_range) in model_name_param_dict.items():
_, best_score, mean_duration = utils.train_test_model(
X_train, y_train, X_test, y_test, model_name, model, param_range)
results_df.loc[model_name, 'AUC'] = best_score
results_df.loc[model_name, 'Time (s)'] = mean_duration
results_df.to_csv(os.path.join(config.output_path, 'model_comparison.csv'))
# 模型及结果比较
print('\n===================== 模型及结果比较 =====================')
plt.figure(figsize=(10, 4))
ax1 = plt.subplot(1, 2, 1)
results_df.plot(y=['AUC'],
kind='bar',
ylim=[0, 1],
ax=ax1,
title='AUC',
legend=False)
ax2 = plt.subplot(1, 2, 2)
results_df.plot(y=['Time (s)'],
kind='bar',
ax=ax2,
title='Time(s)',
legend=False)
plt.tight_layout()
plt.savefig(os.path.join(config.output_path, 'pred_results.png'))
plt.show()