aigroup-econ-mcp 0.4.2__py3-none-any.whl → 1.4.3__py3-none-any.whl

econometrics/model_specification_diagnostics_robust_inference/weighted_least_squares/wls_model.py

@@ -0,0 +1,127 @@
+"""
+加权最小二乘法 (Weighted Least Squares, WLS) 模型实现
+"""
+
+from typing import List, Dict, Any, Optional
+from dataclasses import dataclass
+from pydantic import BaseModel, Field
+import numpy as np
+import pandas as pd
+from scipy import stats
+import statsmodels.api as sm
+
+from tools.decorators import with_file_support_decorator as econometric_tool, validate_input
+
+
+class WLSResult(BaseModel):
+    """WLS回归结果"""
+    coefficients: List[float] = Field(..., description="回归系数")
+    std_errors: List[float] = Field(..., description="系数标准误")
+    t_values: List[float] = Field(..., description="t统计量")
+    p_values: List[float] = Field(..., description="p值")
+    conf_int_lower: List[float] = Field(..., description="置信区间下界")
+    conf_int_upper: List[float] = Field(..., description="置信区间上界")
+    r_squared: float = Field(..., description="R方")
+    adj_r_squared: float = Field(..., description="调整R方")
+    f_statistic: float = Field(..., description="F统计量")
+    f_p_value: float = Field(..., description="F统计量p值")
+    n_obs: int = Field(..., description="观测数量")
+    feature_names: List[str] = Field(..., description="特征名称")
+    weights: List[float] = Field(..., description="使用的权重")
+
+
+@econometric_tool("wls_regression")
+@validate_input(data_type="econometric")
+def wls_regression(
+    y_data: List[float],
+    x_data: List[List[float]], 
+    weights: List[float],
+    feature_names: Optional[List[str]] = None,
+    constant: bool = True,
+    confidence_level: float = 0.95
+) -> WLSResult:
+    """
+    加权最小二乘法回归
+    
+    Args:
+        y_data: 因变量数据
+        x_data: 自变量数据
+        weights: 权重列表（与观测值一一对应）
+        feature_names: 特征名称
+        constant: 是否包含常数项
+        confidence_level: 置信水平
+        
+    Returns:
+        WLSResult: WLS回归结果
+    """
+    # 转换为numpy数组
+    y = np.asarray(y_data, dtype=np.float64)
+    X = np.asarray(x_data, dtype=np.float64)
+    w = np.asarray(weights, dtype=np.float64)
+    
+    # 检查数据维度
+    if len(w) != len(y):
+        raise ValueError("权重数量必须与观测值数量相同")
+    
+    # 检查权重是否为正数
+    if np.any(w <= 0):
+        raise ValueError("所有权重必须为正数")
+    
+    # 添加常数项
+    if constant:
+        X = sm.add_constant(X)
+        if feature_names:
+            feature_names = ["const"] + feature_names
+        else:
+            feature_names = [f"x{i}" for i in range(X.shape[1])]
+    else:
+        if not feature_names:
+            feature_names = [f"x{i}" for i in range(X.shape[1])]
+    
+    # 检查数据维度
+    n, k = X.shape
+    if n <= k:
+        raise ValueError(f"观测数量({n})必须大于变量数量({k})")
+    
+    # 使用statsmodels执行WLS回归
+    try:
+        model = sm.WLS(y, X, weights=w)
+        results = model.fit()
+    except Exception as e:
+        raise ValueError(f"无法拟合WLS模型: {str(e)}")
+    
+    # 提取结果
+    coefficients = results.params.tolist()
+    std_errors = results.bse.tolist()
+    t_values = results.tvalues.tolist()
+    p_values = results.pvalues.tolist()
+    
+    # 计算置信区间
+    alpha = 1 - confidence_level
+    conf_int = results.conf_int(alpha=alpha)
+    conf_int_lower = conf_int[:, 0].tolist()
+    conf_int_upper = conf_int[:, 1].tolist()
+    
+    # 其他统计量
+    r_squared = float(results.rsquared)
+    adj_r_squared = float(results.rsquared_adj)
+    
+    # F统计量
+    f_statistic = float(results.fvalue) if not np.isnan(results.fvalue) else 0.0
+    f_p_value = float(results.f_pvalue) if not np.isnan(results.f_pvalue) else 1.0
+    
+    return WLSResult(
+        coefficients=coefficients,
+        std_errors=std_errors,
+        t_values=t_values,
+        p_values=p_values,
+        conf_int_lower=conf_int_lower,
+        conf_int_upper=conf_int_upper,
+        r_squared=r_squared,
+        adj_r_squared=adj_r_squared,
+        f_statistic=f_statistic,
+        f_p_value=f_p_value,
+        n_obs=int(results.nobs),
+        feature_names=feature_names,
+        weights=weights
+    )

econometrics/specific_data_modeling/time_series_panel_data/__init__.py

@@ -0,0 +1,143 @@
+"""
+时间序列与面板数据模块
+"""
+
+# ARIMA模型
+from .arima_model import (
+    ARIMAResult,
+    arima_model
+)
+
+# 指数平滑法
+from .exponential_smoothing import (
+    ExponentialSmoothingResult,
+    exponential_smoothing_model
+)
+
+# VAR/SVAR模型
+from .var_svar_model import (
+    VARResult,
+    var_model,
+    svar_model
+)
+
+# GARCH模型
+from .garch_model import (
+    GARCHResult,
+    garch_model
+)
+
+# 协整分析/VECM
+from .cointegration_vecm import (
+    CointegrationResult,
+    VECMResult,
+    engle_granger_cointegration_test,
+    johansen_cointegration_test,
+    vecm_model
+)
+
+# 面板VAR
+from .panel_var import (
+    PanelVARResult,
+    panel_var_model
+)
+
+# 单位根检验
+from .unit_root_tests import (
+    UnitRootTestResult,
+    adf_test,
+    pp_test,
+    kpss_test
+)
+
+# 动态面板模型
+from .dynamic_panel_models import (
+    DynamicPanelResult,
+    diff_gmm_model,
+    sys_gmm_model
+)
+
+# 结构突变检验
+from .structural_break_tests import (
+    StructuralBreakResult,
+    chow_test,
+    quandt_andrews_test,
+    bai_perron_test
+)
+
+# 面板数据诊断
+from .panel_diagnostics import (
+    PanelDiagnosticResult,
+    hausman_test,
+    pooling_f_test,
+    lm_test,
+    within_correlation_test
+)
+
+# 时变参数模型
+from .time_varying_parameter_models import (
+    TimeVaryingParameterResult,
+    tar_model,
+    star_model,
+    markov_switching_model
+)
+
+__all__ = [
+    # ARIMA模型
+    "ARIMAResult",
+    "arima_model",
+    
+    # 指数平滑法
+    "ExponentialSmoothingResult",
+    "exponential_smoothing_model",
+    
+    # VAR/SVAR模型
+    "VARResult",
+    "var_model",
+    "svar_model",
+    
+    # GARCH模型
+    "GARCHResult",
+    "garch_model",
+    
+    # 协整分析/VECM
+    "CointegrationResult",
+    "VECMResult",
+    "engle_granger_cointegration_test",
+    "johansen_cointegration_test",
+    "vecm_model",
+    
+    # 面板VAR
+    "PanelVARResult",
+    "panel_var_model",
+    
+    # 单位根检验
+    "UnitRootTestResult",
+    "adf_test",
+    "pp_test",
+    "kpss_test",
+    
+    # 动态面板模型
+    "DynamicPanelResult",
+    "diff_gmm_model",
+    "sys_gmm_model",
+    
+    # 结构突变检验
+    "StructuralBreakResult",
+    "chow_test",
+    "quandt_andrews_test",
+    "bai_perron_test",
+    
+    # 面板数据诊断
+    "PanelDiagnosticResult",
+    "hausman_test",
+    "pooling_f_test",
+    "lm_test",
+    "within_correlation_test",
+    
+    # 时变参数模型
+    "TimeVaryingParameterResult",
+    "tar_model",
+    "star_model",
+    "markov_switching_model"
+]

econometrics/specific_data_modeling/time_series_panel_data/arima_model.py

@@ -0,0 +1,104 @@
+"""
+ARIMA模型实现
+"""
+
+from typing import List, Optional
+from pydantic import BaseModel, Field
+import numpy as np
+
+
+class ARIMAResult(BaseModel):
+    """ARIMA模型结果"""
+    model_type: str = Field(..., description="模型类型")
+    order: tuple = Field(..., description="模型阶数(p, d, q)")
+    coefficients: List[float] = Field(..., description="回归系数")
+    std_errors: Optional[List[float]] = Field(None, description="系数标准误")
+    t_values: Optional[List[float]] = Field(None, description="t统计量")
+    p_values: Optional[List[float]] = Field(None, description="p值")
+    conf_int_lower: Optional[List[float]] = Field(None, description="置信区间下界")
+    conf_int_upper: Optional[List[float]] = Field(None, description="置信区间上界")
+    aic: Optional[float] = Field(None, description="赤池信息准则")
+    bic: Optional[float] = Field(None, description="贝叶斯信息准则")
+    hqic: Optional[float] = Field(None, description="汉南-奎因信息准则")
+    r_squared: Optional[float] = Field(None, description="R方")
+    adj_r_squared: Optional[float] = Field(None, description="调整R方")
+    n_obs: int = Field(..., description="观测数量")
+    forecast: Optional[List[float]] = Field(None, description="预测值")
+
+
+def arima_model(
+    data: List[float],
+    order: tuple = (1, 1, 1),
+    forecast_steps: int = 1
+) -> ARIMAResult:
+    """
+    ARIMA模型实现
+    
+    Args:
+        data: 时间序列数据
+        order: (p,d,q) 参数设置
+        forecast_steps: 预测步数
+        
+    Returns:
+        ARIMAResult: ARIMA模型结果
+    """
+    try:
+        # 导入statsmodels ARIMA模型
+        from statsmodels.tsa.arima.model import ARIMA as StatsARIMA
+        from statsmodels.tsa.stattools import arma_order_select_ic
+        
+        # 拟合ARIMA模型
+        model = StatsARIMA(data, order=order)
+        fitted_model = model.fit()
+        
+        # 提取模型参数
+        params = fitted_model.params.tolist()
+        std_errors = fitted_model.bse.tolist() if fitted_model.bse is not None else None
+        t_values = fitted_model.tvalues.tolist() if fitted_model.tvalues is not None else None
+        p_values = fitted_model.pvalues.tolist() if fitted_model.pvalues is not None else None
+        
+        # 计算置信区间
+        if fitted_model.conf_int() is not None:
+            conf_int = fitted_model.conf_int()
+            conf_int_lower = conf_int[:, 0].tolist()
+            conf_int_upper = conf_int[:, 1].tolist()
+        else:
+            conf_int_lower = None
+            conf_int_upper = None
+            
+        # 进行预测
+        forecast_result = fitted_model.forecast(steps=forecast_steps)
+        forecast = forecast_result.tolist()
+        
+        # 获取模型统计信息
+        aic = float(fitted_model.aic) if hasattr(fitted_model, 'aic') else None
+        bic = float(fitted_model.bic) if hasattr(fitted_model, 'bic') else None
+        hqic = float(fitted_model.hqic) if hasattr(fitted_model, 'hqic') else None
+        
+        # 对于ARIMA模型，通常不计算R方，因为它是基于预测误差而不是解释方差
+        # 但我们仍可以尝试获取，如果没有就设为None
+        r_squared = float(getattr(fitted_model, 'rsquared', None)) if hasattr(fitted_model, 'rsquared') else None
+        adj_r_squared = float(getattr(fitted_model, 'rsquared_adj', None)) if hasattr(fitted_model, 'rsquared_adj') else None
+        
+        p, d, q = order
+        
+        return ARIMAResult(
+            model_type=f"ARIMA({p},{d},{q})",
+            order=order,
+            coefficients=params,
+            std_errors=std_errors,
+            t_values=t_values,
+            p_values=p_values,
+            conf_int_lower=conf_int_lower,
+            conf_int_upper=conf_int_upper,
+            aic=aic,
+            bic=bic,
+            hqic=hqic,
+            r_squared=r_squared,
+            adj_r_squared=adj_r_squared,
+            n_obs=len(data),
+            forecast=forecast
+        )
+    except Exception as e:
+        # 出现错误时抛出异常
+        raise ValueError(f"ARIMA模型拟合失败: {str(e)}")