mcnemar_utils.py

import plotly.graph_objects as go
import plotly.express as px
import pandas as pd
import numpy as np

def plot_contingency_table_heatmap(ct_labeled, feature_label, title="列聯表熱力圖"):
    """
    繪製列聯表熱力圖
    
    Args:
        ct_labeled: 帶標籤的列聯表 DataFrame
        feature_label: 特徵標籤
        title: 圖表標題
        
    Returns:
        plotly figure
    """
    # 移除總數列和行
    ct_display = ct_labeled.iloc[:-1, :-1].copy()
    
    # 創建註解文字
    annotations = []
    for i, row in enumerate(ct_display.index):
        for j, col in enumerate(ct_display.columns):
            annotations.append(
                dict(
                    x=j,
                    y=i,
                    text=str(ct_display.iloc[i, j]),
                    font=dict(size=16, color='white' if ct_display.iloc[i, j] > ct_display.values.max()/2 else 'black'),
                    showarrow=False
                )
            )
    
    fig = go.Figure(data=go.Heatmap(
        z=ct_display.values,
        x=ct_display.columns,
        y=ct_display.index,
        colorscale='Blues',
        showscale=True,
        hoverongaps=False,
        hovertemplate='%{y}<br>%{x}<br>配對數: %{z}<extra></extra>'
    ))
    
    fig.update_layout(
        title=f'{title}<br><sub>{feature_label}</sub>',
        xaxis_title='敗方 (Loser)',
        yaxis_title='勝方 (Winner)',
        width=600,
        height=500,
        template='plotly_white',
        annotations=annotations
    )
    
    return fig

def plot_odds_ratio_forest(or_value, ci_low, ci_high, feature_label):
    """
    繪製勝算比森林圖（線性刻度版本）
    
    Args:
        or_value: 勝算比
        ci_low: 95% 信賴區間下界
        ci_high: 95% 信賴區間上界
        feature_label: 特徵標籤
        
    Returns:
        plotly figure
    """
    fig = go.Figure()
    
    # 動態計算 x 軸範圍
    x_max = max(ci_high * 1.2, 3.5)  # 至少到 3.5
    x_min = 0
    
    # 參考線 (OR = 1)
    fig.add_shape(
        type="line",
        x0=1, x1=1,
        y0=-0.3, y1=0.3,
        line=dict(color="red", width=2, dash="dash"),
    )
    
    # 信賴區間（水平線）
    fig.add_trace(go.Scatter(
        x=[ci_low, ci_high],
        y=[0, 0],
        mode='lines',
        line=dict(color='#2d6ca2', width=2),
        showlegend=False,
        hoverinfo='skip'
    ))
    
    # 信賴區間端點（小豎線）
    for x_pos in [ci_low, ci_high]:
        fig.add_shape(
            type="line",
            x0=x_pos, x1=x_pos,
            y0=-0.05, y1=0.05,
            line=dict(color='#2d6ca2', width=2)
        )
    
    # 點估計（藍色圓點）
    fig.add_trace(go.Scatter(
        x=[or_value],
        y=[0],
        mode='markers',
        marker=dict(
            size=12,
            color='#1f77b4',
            line=dict(color='white', width=1.5)
        ),
        showlegend=False,
        hovertemplate=f'<b>OR: {or_value:.3f}</b><br>95% CI: [{ci_low:.3f}, {ci_high:.3f}]<extra></extra>'
    ))
    
    # 添加數值標註框（右上角）
    fig.add_annotation(
        x=ci_high + (x_max - ci_high) * 0.3,
        y=0,
        text=f"OR = {or_value:.3f}<br>95% CI [{ci_low:.3f}, {ci_high:.3f}]",
        showarrow=True,
        arrowhead=2,
        arrowsize=1,
        arrowwidth=1.5,
        arrowcolor='#2d6ca2',
        ax=50,
        ay=0,
        font=dict(size=11, color='#1b4f72'),
        bgcolor='rgba(255,255,255,0.95)',
        bordercolor='#2d6ca2',
        borderwidth=1.5,
        borderpad=6
    )
    
    fig.update_layout(
        title=dict(
            text=f'勝算比 (Odds Ratio)<br><sub style="font-size:11px;">{feature_label}</sub>',
            x=0.5,
            xanchor='center'
        ),
        xaxis_title='Odds Ratio',
        yaxis=dict(
            showticklabels=False,
            showgrid=False,
            zeroline=False,
            range=[-0.35, 0.35]
        ),
        width=800,
        height=280,
        template='plotly_white',
        xaxis=dict(
            type='linear',  # 改用線性刻度
            showgrid=True,
            gridcolor='rgba(200,200,200,0.3)',
            tickmode='linear',
            tick0=0,
            dtick=0.5,  # 每 0.5 一個刻度
            range=[x_min, x_max],
            showline=True,
            linewidth=1,
            linecolor='black',
            mirror=True
        ),
        hovermode='closest',
        plot_bgcolor='white',
        margin=dict(l=60, r=60, t=80, b=60)
    )
    
    return fig


def plot_discordant_pairs(b, c, label_pos, label_neg):
    """
    繪製不一致配對比較圖
    
    Args:
        b: cs=1 & cn=0 的配對數
        c: cs=0 & cn=1 的配對數
        label_pos: 正向標籤
        label_neg: 負向標籤
        
    Returns:
        plotly figure
    """
    fig = go.Figure()
    
    categories = [
        f'勝方 {label_pos.split()[1]}<br>敗方 {label_neg.split()[1]}',
        f'勝方 {label_neg.split()[1]}<br>敗方 {label_pos.split()[1]}'
    ]
    values = [b, c]
    colors = ['#2d6ca2', '#d62728']
    
    fig.add_trace(go.Bar(
        x=categories,
        y=values,
        marker=dict(
            color=colors,
            line=dict(color='white', width=2)
        ),
        text=values,
        textposition='outside',
        textfont=dict(size=16, color='black'),
        hovertemplate='%{x}<br>配對數: %{y}<extra></extra>'
    ))
    
    fig.update_layout(
        title='不一致配對分布',
        xaxis_title='配對類型',
        yaxis_title='配對數量',
        width=600,
        height=400,
        template='plotly_white',
        showlegend=False
    )
    
    return fig

def plot_p_value_significance(p_value):
    """
    繪製 p 值顯著性指示圖
    
    Args:
        p_value: p 值
        
    Returns:
        plotly figure
    """
    fig = go.Figure()
    
    # 設定顯著性閾值
    thresholds = [0.001, 0.01, 0.05, 1.0]
    labels = ['p < 0.001<br>(極顯著)', 'p < 0.01<br>(非常顯著)', 
              'p < 0.05<br>(顯著)', 'p ≥ 0.05<br>(不顯著)']
    colors = ['#1a5f1a', '#2d8b2d', '#5cb85c', '#d9534f']
    
    # 找出 p 值所在區間
    current_idx = 0
    for i, thresh in enumerate(thresholds):
        if p_value < thresh:
            current_idx = i
            break
    
    # 繪製區間條
    for i in range(len(thresholds)):
        opacity = 1.0 if i == current_idx else 0.3
        fig.add_trace(go.Bar(
            x=[labels[i]],
            y=[1],
            marker=dict(color=colors[i], opacity=opacity),
            showlegend=False,
            hovertemplate=f'{labels[i]}<extra></extra>'
        ))
    
    # 添加 p 值標註
    fig.add_annotation(
        x=labels[current_idx],
        y=1.1,
        text=f"<b>p = {p_value:.4f}</b>",
        showarrow=True,
        arrowhead=2,
        arrowsize=1,
        arrowwidth=2,
        arrowcolor='black',
        font=dict(size=14, color='black'),
        bgcolor='yellow',
        bordercolor='black',
        borderwidth=2,
        borderpad=4
    )
    
    fig.update_layout(
        title='顯著性水準',
        xaxis_title='',
        yaxis_title='',
        yaxis=dict(showticklabels=False, showgrid=False),
        width=700,
        height=300,
        template='plotly_white',
        showlegend=False
    )
    
    return fig

def create_results_summary_table(results):
    """
    創建結果摘要表格
    
    Args:
        results: 分析結果字典
        
    Returns:
        pandas DataFrame
    """
    summary_data = {
        '項目': [
            '特徵',
            'McNemar 統計量',
            'p 值',
            '顯著性',
            '勝算比 (OR)',
            '95% 信賴區間',
            '不一致配對數',
            '效果大小'
        ],
        '數值': [
            results['feature_label'],
            f"{results['mcnemar_statistic']:.4f}",
            f"{results['p_value']:.4f}",
            results['interpretation']['significance'],
            f"{results['odds_ratio']:.3f}",
            f"[{results['ci_low']:.3f}, {results['ci_high']:.3f}]",
            f"{results['discordant_n']} (b={results['discordant_b']}, c={results['discordant_c']})",
            results['interpretation']['effect_size']
        ]
    }
    
    return pd.DataFrame(summary_data)

def export_results_to_text(results):
    """
    匯出結果為純文字格式
    
    Args:
        results: 分析結果字典
        
    Returns:
        str: 格式化的文字報告
    """
    report = f"""
==============================================
McNemar 檢定分析報告
==============================================

分析特徵: {results['feature_label']} ({results['feature_name']})
分析時間: {results['timestamp']}

----------------------------------------------
1. 列聯表
----------------------------------------------
{results['contingency_table_labeled'].to_string()}

----------------------------------------------
2. McNemar 檢定結果
----------------------------------------------
McNemar 統計量: {results['mcnemar_statistic']:.4f}
p 值: {results['p_value']:.4f}
顯著性: {results['interpretation']['significance']}

----------------------------------------------
3. 勝算比分析
----------------------------------------------
勝算比 (OR): {results['odds_ratio']:.3f}
95% 信賴區間: [{results['ci_low']:.3f}, {results['ci_high']:.3f}]
效果大小: {results['interpretation']['effect_size']}

----------------------------------------------
4. 不一致配對
----------------------------------------------
勝方{results['label_pos'].split()[1]}且敗方{results['label_neg'].split()[1]} (b): {results['discordant_b']}
勝方{results['label_neg'].split()[1]}且敗方{results['label_pos'].split()[1]} (c): {results['discordant_c']}
總不一致配對數: {results['discordant_n']}

----------------------------------------------
5. 解釋
----------------------------------------------
{'結果顯示勝方和敗方在此特徵上有顯著差異。' if results['interpretation']['is_significant'] else '結果顯示勝方和敗方在此特徵上無顯著差異。'}
勝算比為 {results['odds_ratio']:.3f}，表示{
    '勝方在此特徵上較高的機率是敗方的 ' + str(round(results['odds_ratio'], 2)) + ' 倍。' 
    if results['odds_ratio'] > 1 
    else '敗方在此特徵上較高的機率是勝方的 ' + str(round(1/results['odds_ratio'], 2)) + ' 倍。'
}

==============================================
"""
    return report