86 lines
2.9 KiB
Python
86 lines
2.9 KiB
Python
import pandas as pd
|
|
from sklearn.linear_model import LassoCV, Lasso
|
|
from sklearn.preprocessing import StandardScaler
|
|
import json
|
|
import sys
|
|
|
|
# 重新配置标准输出流的编码为 UTF-8
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
|
|
|
|
def load_data(file_path):
|
|
with open(file_path, 'r', encoding='utf-8') as file:
|
|
json_str = file.read()
|
|
|
|
# 解析 JSON 字符串
|
|
data_dict = json.loads(json_str)
|
|
# 转为 Pandas DataFrame
|
|
data = pd.DataFrame(data_dict)
|
|
|
|
# # """加载数据并重命名列"""
|
|
# data = pd.read_csv(file_path)
|
|
new_names = [f'q{i}' for i in range(7, 189)]
|
|
data.columns.values[6:189] = new_names
|
|
return data
|
|
|
|
|
|
def prepare_data(data):
|
|
data['month'] = data['month'].astype(int)
|
|
data['year'] = data['year'].astype(int)
|
|
# """选择所需的数据，计算平均值并合并数据"""
|
|
new_names = [f'q{i}' for i in range(7, 189)] # 确保此列名称与选择特征匹配
|
|
selected_data = (
|
|
data[(data['year'] == 2021) | (data['year'] == 2022) | ((data['year'] == 2023) & (data['month'] <= 5))]
|
|
.groupby('area_name')[new_names].mean().reset_index()
|
|
)
|
|
all_score_2023_06 = data[(data['year'] == 2023) & (data['month'] == 6)].dropna(subset=['all_score'])[
|
|
['area_name', 'all_score']]
|
|
model_data = pd.merge(selected_data, all_score_2023_06, on='area_name')
|
|
return model_data
|
|
|
|
|
|
def train_lasso(X, y):
|
|
"""训练LASSO回归模型并返回最佳模型和预测值"""
|
|
scaler = StandardScaler()
|
|
X_scaled = scaler.fit_transform(X)
|
|
lasso_cv = LassoCV(cv=16, random_state=42).fit(X_scaled, y)
|
|
best_lambda = lasso_cv.alpha_
|
|
lasso_model = Lasso(alpha=best_lambda).fit(X_scaled, y)
|
|
predictions = lasso_model.predict(X_scaled)
|
|
return lasso_model, predictions, best_lambda, lasso_cv
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
# 1. 加载数据
|
|
file_path = sys.argv[1]
|
|
data = load_data(file_path)
|
|
# data = load_data(
|
|
# "H:/develop/dama/java/buliangfanying/src/main/resources/python/二级指标加权分数.csv") # 替换为您的实际文件路径
|
|
|
|
# 2. 准备数据
|
|
model_data = prepare_data(data)
|
|
# 2.1移除所有值相同的列
|
|
model_data = model_data.loc[:, model_data.nunique() > 1]
|
|
|
|
# 3. 准备特征和目标变量
|
|
feature_names = model_data.drop(columns=['area_name', 'all_score']).columns.tolist()
|
|
X = model_data[feature_names].values
|
|
y = model_data['all_score'].values
|
|
|
|
# 保留但不参与计算的列
|
|
columns_to_exclude = ['area_name']
|
|
# 移除不需要参与计算的列
|
|
X_for_model = model_data.drop(columns=columns_to_exclude)
|
|
|
|
# 4. 训练模型
|
|
lasso_model, lasso_predictions, best_lambda, lasso_cv = train_lasso(X, y)
|
|
|
|
result_df = pd.DataFrame({
|
|
'area_name': model_data['area_name'],
|
|
'predicted_score': lasso_predictions
|
|
})
|
|
|
|
# 将 DataFrame 转换为 JSON 字符串并输出
|
|
print(json.dumps(json.loads(result_df.to_json(orient='records')), ensure_ascii=False, indent=4))
|