data1/reporting/visualization.py

"""
Visualization module: Generate publication-ready figures (PNG/SVG)
ACL conference style, 1920x1080 or A4 landscape size
"""
import matplotlib
matplotlib.use('Agg')  # 非交互式后端
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm
import seaborn as sns
import pandas as pd
import numpy as np
from pathlib import Path
import json
import statistics
from collections import Counter

# Font fallback mechanism
# Try Arial, fallback to DejaVu Sans (common on Linux) or sans-serif
font_families_to_try = ['Arial', 'DejaVu Sans', 'Liberation Sans', 'sans-serif']
available_fonts = [f.name for f in fm.fontManager.ttflist]
font_found = None

for font_family in font_families_to_try:
    # Check if font exists (case-insensitive)
    font_lower = font_family.lower()
    if any(f.lower() == font_lower for f in available_fonts):
        font_found = font_family
        break

if font_found is None:
    # If no font found, use default sans-serif
    font_found = 'sans-serif'

# Nature journal style: professional, high-contrast, color-rich
# Large fonts for axis labels and tick values, smaller for titles/legends to avoid overlap
# Increased font sizes for PPT presentation
plt.rcParams['font.family'] = font_found
plt.rcParams['font.size'] = 24
plt.rcParams['axes.labelsize'] = 42  # Large axis labels (increased from 32)
plt.rcParams['axes.titlesize'] = 30  # Titles (increased from 20)
plt.rcParams['xtick.labelsize'] = 36  # Large tick values (increased from 28)
plt.rcParams['ytick.labelsize'] = 36  # Large tick values (increased from 28)
plt.rcParams['legend.fontsize'] = 20  # Legend (increased from 16)
plt.rcParams['figure.titlesize'] = 32  # Figure titles (increased from 24)
plt.rcParams['axes.linewidth'] = 1.5
plt.rcParams['axes.spines.top'] = False
plt.rcParams['axes.spines.right'] = False
plt.rcParams['axes.grid'] = True
plt.rcParams['grid.alpha'] = 0.3
plt.rcParams['grid.linewidth'] = 0.5
plt.rcParams['axes.unicode_minus'] = False

# Nature color scheme (high contrast, professional)
NATURE_COLORS = {
    'primary': '#2E5090',      # Nature blue
    'secondary': '#1A5490',
    'accent': '#4A90E2',
    'success': '#2E7D32',
    'warning': '#F57C00',
    'error': '#C62828',
    'neutral': '#424242',
    'light': '#E3F2FD'
}

# Nature style palette
nature_palette = ['#2E5090', '#4A90E2', '#1A5490', '#6BA3D8', '#94C4E8']


class Visualization:
    def __init__(self, output_dir, figsize=(19.2, 10.8), dpi=150):
        self.output_dir = Path(output_dir)
        self.output_dir.mkdir(parents=True, exist_ok=True)
        self.figsize = figsize
        self.dpi = dpi  # 提高DPI以获得更清晰的图片
        self.fig_counter = 1
        
    def apply_nature_style(self, ax):
        """Apply Nature journal style to axes"""
        ax.spines['top'].set_visible(False)
        ax.spines['right'].set_visible(False)
        ax.spines['left'].set_linewidth(1.5)
        ax.spines['bottom'].set_linewidth(1.5)
        ax.grid(True, alpha=0.3, linestyle='--', linewidth=0.5)
        ax.tick_params(width=1.5, length=5)
    
    def save_fig(self, fig, name):
        """保存图片"""
        fig_path_png = self.output_dir / f"fig_{self.fig_counter:02d}_{name}.png"
        fig_path_svg = self.output_dir / f"fig_{self.fig_counter:02d}_{name}.svg"
        fig.savefig(fig_path_png, dpi=self.dpi, bbox_inches='tight', facecolor='white')
        fig.savefig(fig_path_svg, bbox_inches='tight', facecolor='white')
        plt.close(fig)
        self.fig_counter += 1
        print(f"Saved: {fig_path_png}")
    
    def plot_funnel(self, stage_a_dir, stage_b_dir, repo_meta_dir, top_n=None):
        """绘制漏斗图：搜索->过滤->深度分析"""
        # 读取数据
        stage_a_path = Path(stage_a_dir) / 'summary_overall.json'
        stage_b_path = Path(stage_b_dir) / 'filter_summary.json'
        repo_meta_path = Path(repo_meta_dir) / 'repo_meta_summary.json'
        
        with open(stage_a_path, 'r') as f:
            stage_a = json.load(f)
        
        with open(stage_b_path, 'r') as f:
            stage_b = json.load(f)
        
        # 尝试读取repo_meta数据获取实际数量
        deep_analysis_count = top_n if top_n else 0
        try:
            with open(repo_meta_path, 'r') as f:
                repo_meta = json.load(f)
                deep_analysis_count = repo_meta.get('total_repos', deep_analysis_count)
        except:
            pass
        
        # 动态生成标签
        if top_n:
            deep_analysis_label = f'Deep Analysis\n({top_n:,} repos)'
        else:
            deep_analysis_label = f'Deep Analysis\n({deep_analysis_count:,} repos)'
        
        stages = ['Search Stage\n(~1.3M repos)', 'Filtered\n(~30K repos)', deep_analysis_label]
        values = [
            stage_a['total_records'],
            stage_b['total'],
            deep_analysis_count
        ]
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        # Draw funnel - Use Nature blue gradient
        y_pos = np.arange(len(stages))
        colors = [NATURE_COLORS['primary'], NATURE_COLORS['accent'], NATURE_COLORS['secondary']]
        
        bars = ax.barh(y_pos, values, color=colors, alpha=0.85, edgecolor='white', linewidth=2)
        ax.set_yticks(y_pos)
        ax.set_yticklabels(stages, fontsize=36)
        ax.set_xlabel('Number of Repositories', fontsize=42, fontweight='bold')
        ax.set_title('Data Pipeline: Search → Filter → Deep Analysis', fontsize=30, fontweight='bold', pad=20)
        
        # Add value labels
        for i, (bar, val) in enumerate(zip(bars, values)):
            ax.text(val * 0.5, i, f'{val:,}', ha='center', va='center', 
                   fontsize=24, fontweight='bold', color='white')
        
        ax.invert_yaxis()
        plt.tight_layout()
        
        self.save_fig(fig, 'funnel')
    
    def plot_top_keywords(self, csv_path, top_n=20):
        """绘制Top keywords条形图"""
        df = pd.read_csv(csv_path)
        df_top = df.head(top_n)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        # Use Nature blue
        bars = ax.barh(range(len(df_top)), df_top['count'], 
                      color=NATURE_COLORS['primary'], alpha=0.85, 
                      edgecolor='white', linewidth=1.5)
        ax.set_yticks(range(len(df_top)))
        ax.set_yticklabels(df_top['keyword'], fontsize=36, rotation=15, ha='right')
        ax.set_xlabel('Number of Repositories', fontsize=42, fontweight='bold')
        ax.set_title(f'Top {top_n} Keywords (Search Stage)', fontsize=30, fontweight='bold', pad=20)
        
        # Add value labels
        for i, (idx, row) in enumerate(df_top.iterrows()):
            ax.text(row['count'] * 0.5, i, f"{int(row['count']):,}", 
                   ha='center', va='center', fontsize=24, fontweight='bold', color='white')
        
        ax.invert_yaxis()
        plt.tight_layout()
        
        self.save_fig(fig, 'top_keywords')
    
    def plot_language_distribution(self, csv_path, top_n=15):
        """绘制语言分布"""
        df = pd.read_csv(csv_path)
        df = df[df['language'] != '<empty>'].head(top_n)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        bars = ax.bar(range(len(df)), df['count'], 
                     color=NATURE_COLORS['primary'], alpha=0.85,
                     edgecolor='white', linewidth=1.5)
        ax.set_xticks(range(len(df)))
        ax.set_xticklabels(df['language'], rotation=45, ha='right', fontsize=36)
        ax.set_ylabel('Number of Repositories', fontsize=42, fontweight='bold')
        ax.set_title(f'Top {top_n} Programming Languages (Search Stage)', 
                    fontsize=30, fontweight='bold', pad=20)
        
        # 添加数值标签（旋转45度避免重叠）
        for i, count in enumerate(df['count']):
            ax.text(i, count, f"{int(count):,}", ha='center', va='bottom', 
                   fontsize=24, fontweight='bold', rotation=45)
        
        plt.tight_layout()
        
        self.save_fig(fig, 'language_distribution')
    
    def plot_stars_distribution(self, csv_path):
        """绘制stars分布（对数坐标）"""
        df = pd.read_csv(csv_path)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        # Use log bins
        log_bins = np.logspace(0, np.log10(df['stars'].max() + 1), 50)
        ax.hist(df['stars'], bins=log_bins, 
               color=NATURE_COLORS['primary'], alpha=0.75, 
               edgecolor='white', linewidth=1)
        ax.set_xscale('log')
        ax.set_xlabel('Stars (log scale)', fontsize=42, fontweight='bold')
        ax.set_ylabel('Number of Repositories', fontsize=42, fontweight='bold')
        ax.set_title('Distribution of Repository Stars (Log Scale)', 
                    fontsize=30, fontweight='bold', pad=20)
        
        plt.tight_layout()
        
        self.save_fig(fig, 'stars_distribution')
    
    def plot_filter_results(self, csv_path):
        """绘制过滤结果（按keyword的YES/NO）"""
        df = pd.read_csv(csv_path)
        df = df.head(15)  # Top 15 keywords
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        x = np.arange(len(df))
        width = 0.4
        
        bars1 = ax.bar(x - width/2, df['yes'], width, label='Relevant (YES)', 
                      color=NATURE_COLORS['success'], alpha=0.85, edgecolor='white', linewidth=1.5)
        bars2 = ax.bar(x + width/2, df['no'], width, label='Irrelevant (NO)', 
                      color=NATURE_COLORS['error'], alpha=0.85, edgecolor='white', linewidth=1.5)
        
        ax.set_xlabel('Keyword', fontsize=42, fontweight='bold')
        ax.set_ylabel('Number of Repositories', fontsize=42, fontweight='bold')
        ax.set_title('Filter Results: YES/NO Distribution by Keyword', 
                    fontsize=30, fontweight='bold', pad=20)
        ax.set_xticks(x)
        ax.set_xticklabels(df['keyword'], rotation=45, ha='right', fontsize=36)
        ax.legend(fontsize=20, frameon=True, fancybox=True, shadow=True)
        
        plt.tight_layout()
        
        self.save_fig(fig, 'filter_results_by_keyword')
    
    def plot_reason_length_comparison(self, csv_path):
        """绘制reason长度对比（YES vs NO）"""
        df = pd.read_csv(csv_path)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        yes_lengths = df[df['label'] == 'YES']['length']
        no_lengths = df[df['label'] == 'NO']['length']
        
        bp = ax.boxplot([yes_lengths, no_lengths], labels=['YES', 'NO'], 
                       patch_artist=True,
                       widths=0.6,
                       boxprops=dict(facecolor=NATURE_COLORS['primary'], alpha=0.7, linewidth=2),
                       medianprops=dict(color='white', linewidth=3),
                       whiskerprops=dict(linewidth=2),
                       capprops=dict(linewidth=2),
                       flierprops=dict(marker='o', markersize=8, alpha=0.5))
        
        ax.set_ylabel('Reason Length (Characters)', fontsize=42, fontweight='bold')
        ax.set_title('Comparison of Filter Reason Length: YES vs NO', 
                    fontsize=30, fontweight='bold', pad=20)
        ax.set_xticklabels(['Relevant (YES)', 'Irrelevant (NO)'], fontsize=36)
        
        plt.tight_layout()
        
        self.save_fig(fig, 'reason_length_comparison')
    
    def plot_extension_distribution(self, csv_path, top_n=20, repo_top_n=None):
        """绘制文件扩展名分布"""
        df = pd.read_csv(csv_path)
        df = df.head(top_n)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        bars = ax.barh(range(len(df)), df['count'], 
                      color=NATURE_COLORS['accent'], alpha=0.85,
                      edgecolor='white', linewidth=1.5)
        ax.set_yticks(range(len(df)))
        ax.set_yticklabels(df['extension'], fontsize=36, rotation=15, ha='right')
        ax.set_xlabel('Number of Files', fontsize=42, fontweight='bold')
        
        # 动态生成标题
        if repo_top_n:
            repo_label = f'Top {repo_top_n:,} Repositories'
        else:
            repo_label = 'All Repositories'
        ax.set_title(f'Top {top_n} File Extension Distribution ({repo_label})', 
                    fontsize=30, fontweight='bold', pad=20)
        
        ax.invert_yaxis()
        plt.tight_layout()
        
        self.save_fig(fig, 'extension_distribution')
    
    def plot_repo_file_count_distribution(self, csv_path, repo_top_n=None):
        """绘制仓库文件数分布"""
        df = pd.read_csv(csv_path)
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        # Use log bins (file counts may span large ranges)
        log_bins = np.logspace(0, np.log10(df['total_files'].max() + 1), 50)
        ax.hist(df['total_files'], bins=log_bins, 
               color=NATURE_COLORS['primary'], alpha=0.75, 
               edgecolor='white', linewidth=1)
        ax.set_xscale('log')
        ax.set_xlabel('Number of Files (log scale)', fontsize=42, fontweight='bold')
        ax.set_ylabel('Number of Repositories', fontsize=42, fontweight='bold')
        
        # 动态生成标题
        if repo_top_n:
            repo_label = f'Top {repo_top_n:,} Repositories'
        else:
            repo_label = 'All Repositories'
        ax.set_title(f'Distribution of Repository File Counts ({repo_label})', 
                    fontsize=30, fontweight='bold', pad=20)
        
        plt.tight_layout()
        
        self.save_fig(fig, 'repo_file_count_distribution')
    
    def plot_stars_vs_code_size(self, repos_searched_csv, repo_level_csv, repo_top_n=None):
        """绘制stars vs 代码规模散点图（需要join）"""
        # 读取repos_searched获取stars
        df_searched = pd.read_csv(repos_searched_csv, usecols=['full_name', 'stars'])
        df_searched = df_searched.dropna(subset=['stars'])
        df_searched['stars'] = df_searched['stars'].astype(float)
        
        # 读取repo_level统计
        df_repo = pd.read_csv(repo_level_csv)
        df_repo['full_name'] = df_repo['full_name'].fillna(df_repo['repo_name'].str.replace('___', '/'))
        
        # Join
        df_merged = df_repo.merge(df_searched, on='full_name', how='inner')
        df_merged = df_merged[df_merged['total_code_lines'] > 0]
        
        if len(df_merged) == 0:
            print("Warning: No data to plot stars vs code size")
            return
        
        fig, ax = plt.subplots(figsize=self.figsize)
        self.apply_nature_style(ax)
        
        # Log scale, use Nature blue, increase transparency
        ax.scatter(df_merged['total_code_lines'], df_merged['stars'], 
                  alpha=0.4, s=30, color=NATURE_COLORS['primary'], edgecolors='white', linewidth=0.5)
        ax.set_xscale('log')
        ax.set_yscale('log')
        ax.set_xlabel('Lines of Code (LOC, log scale)', fontsize=42, fontweight='bold')
        ax.set_ylabel('Stars (log scale)', fontsize=42, fontweight='bold')
        
        # 动态生成标题
        if repo_top_n:
            repo_label = f'Top {repo_top_n:,} Repositories'
        else:
            repo_label = 'All Repositories'
        ax.set_title(f'Stars vs Code Size ({repo_label})', 
                    fontsize=30, fontweight='bold', pad=20)
        
        # 添加相关性
        corr = np.corrcoef(np.log10(df_merged['total_code_lines']), 
                          np.log10(df_merged['stars']))[0, 1]
        ax.text(0.05, 0.95, f'Correlation: r = {corr:.3f}', transform=ax.transAxes,
               fontsize=24, verticalalignment='top', fontweight='bold',
               bbox=dict(boxstyle='round', facecolor='white', alpha=0.8, edgecolor=NATURE_COLORS['primary'], linewidth=2))
        
        plt.tight_layout()
        
        self.save_fig(fig, 'stars_vs_code_size')
    
    def plot_repo_stats_by_language(self, repo_level_csv, repo_top_n=None):
        """绘制按主语言的代码统计对比"""
        df = pd.read_csv(repo_level_csv)
        df = df[df['primary_language'] != 'unknown']
        
        # 选择Top 10语言
        top_langs = df['primary_language'].value_counts().head(10).index
        df = df[df['primary_language'].isin(top_langs)]
        
        # 增大图片尺寸以避免字体重叠
        larger_figsize = (24, 16)  # 从默认的 (19.2, 10.8) 增大到 (24, 16)
        fig, axes = plt.subplots(2, 2, figsize=larger_figsize)
        
        colors_list = [NATURE_COLORS['primary'], NATURE_COLORS['accent'], 
                      NATURE_COLORS['success'], NATURE_COLORS['secondary']]
        
        # 1. 平均代码行数
        ax = axes[0, 0]
        self.apply_nature_style(ax)
        lang_stats = df.groupby('primary_language')['total_code_lines'].mean().sort_values(ascending=False)
        lang_stats.plot(kind='bar', ax=ax, color=colors_list[0], alpha=0.85, edgecolor='white', linewidth=1.5)
        ax.set_title('Average Lines of Code', fontsize=28, fontweight='bold', pad=25)
        ax.set_xlabel('')
        ax.set_ylabel('Average LOC', fontsize=42)
        ax.tick_params(axis='x', rotation=45, labelsize=36, pad=10)
        ax.tick_params(axis='y', labelsize=36, pad=10)
        
        # 2. Average number of functions
        ax = axes[0, 1]
        self.apply_nature_style(ax)
        lang_stats = df.groupby('primary_language')['total_functions'].mean().sort_values(ascending=False)
        lang_stats.plot(kind='bar', ax=ax, color=colors_list[1], alpha=0.85, edgecolor='white', linewidth=1.5)
        ax.set_title('Average Number of Functions', fontsize=28, fontweight='bold', pad=25)
        ax.set_xlabel('')
        ax.set_ylabel('Average Functions', fontsize=42)
        ax.tick_params(axis='x', rotation=45, labelsize=36, pad=10)
        ax.tick_params(axis='y', labelsize=36, pad=10)
        
        # 3. Average comment ratio
        ax = axes[1, 0]
        self.apply_nature_style(ax)
        lang_stats = df.groupby('primary_language')['comment_ratio'].mean().sort_values(ascending=False)
        lang_stats.plot(kind='bar', ax=ax, color=colors_list[2], alpha=0.85, edgecolor='white', linewidth=1.5)
        ax.set_title('Average Comment Ratio', fontsize=28, fontweight='bold', pad=25)
        ax.set_xlabel('')
        ax.set_ylabel('Comment Ratio', fontsize=42)
        ax.tick_params(axis='x', rotation=45, labelsize=36, pad=10)
        ax.tick_params(axis='y', labelsize=36, pad=10)
        
        # 4. Language diversity (entropy)
        ax = axes[1, 1]
        self.apply_nature_style(ax)
        lang_stats = df.groupby('primary_language')['language_entropy'].mean().sort_values(ascending=False)
        lang_stats.plot(kind='bar', ax=ax, color=colors_list[3], alpha=0.85, edgecolor='white', linewidth=1.5)
        ax.set_title('Average Language Diversity', fontsize=28, fontweight='bold', pad=25)
        ax.set_xlabel('')
        ax.set_ylabel('Language Entropy', fontsize=42)
        ax.tick_params(axis='x', rotation=45, labelsize=36, pad=10)
        ax.tick_params(axis='y', labelsize=36, pad=10)
        
        # 动态生成标题
        if repo_top_n:
            repo_label = f'Top {repo_top_n:,} Repositories'
        else:
            repo_label = 'All Repositories'
        plt.suptitle(f'Repository Code Statistics by Primary Language ({repo_label})', 
                    fontsize=36, fontweight='bold', y=0.995)
        
        # 大幅增加上下子图之间的垂直间距，并调整其他间距
        # top 调小以给总标题留出更多空间，避免与子图标题重叠
        plt.subplots_adjust(hspace=0.8, wspace=0.4, top=0.88, bottom=0.08, left=0.08, right=0.95)
        
        self.save_fig(plt.gcf(), 'repo_stats_by_language')
    
    def plot_keyword_wordcloud(self, csv_path, max_words=200):
        """Generate wordcloud for keywords (Nature style: colorful)"""
        try:
            from wordcloud import WordCloud
        except ImportError:
            print("Warning: wordcloud library not installed. Skipping wordcloud generation.")
            print("Install with: pip install wordcloud")
            return
        
        try:
            # Read keyword data
            df = pd.read_csv(csv_path)
            
            # Create frequency dictionary - ensure values are integers
            keyword_freq = {}
            for keyword, count in zip(df['keyword'], df['count']):
                keyword_freq[str(keyword)] = int(count)
            
            # Generate wordcloud with Nature style (colorful)
            wordcloud = WordCloud(
                width=1920,
                height=1080,
                background_color='white',
                colormap='Blues',  # Blue colormap for Nature style
                max_words=max_words,
                relative_scaling=0.5,
                min_font_size=10,
                prefer_horizontal=0.7,
                collocations=False
            )
            
            # Generate from frequencies
            wordcloud.generate_from_frequencies(keyword_freq)
            
            # Create figure
            fig, ax = plt.subplots(figsize=self.figsize)
            
            # Convert WordCloud to PIL Image first, then to numpy array
            # This avoids the numpy version compatibility issue with copy parameter
            pil_image = wordcloud.to_image()
            wordcloud_array = np.array(pil_image)
            
            ax.imshow(wordcloud_array, interpolation='bilinear')
            ax.axis('off')
            ax.set_title('Keyword Word Cloud (Search Stage)', 
                        fontsize=30, fontweight='bold', pad=20)
            
            plt.tight_layout()
            
            # Save wordcloud
            fig_path_png = self.output_dir / f"fig_{self.fig_counter:02d}_keyword_wordcloud.png"
            fig.savefig(fig_path_png, dpi=self.dpi, bbox_inches='tight', facecolor='white')
            plt.close(fig)
            self.fig_counter += 1
            print(f"Saved: {fig_path_png}")
            
        except Exception as e:
            print(f"Error generating wordcloud: {e}")
            import traceback
            traceback.print_exc()


def generate_all_visualizations(stage_a_dir, stage_b_dir, repo_meta_dir, code_stats_dir, repos_searched_csv, top_n=None):
    """生成所有图表"""
    viz = Visualization(Path(stage_a_dir).parent / 'figures')
    
    print("Generating visualizations...")
    
    # 动态生成文件名后缀
    top_n_suffix = f"_top{top_n}" if top_n else ""
    
    # Stage A charts
    try:
        viz.plot_funnel(stage_a_dir, stage_b_dir, repo_meta_dir, top_n=top_n)
    except Exception as e:
        print(f"Error plotting funnel: {e}")
    
    try:
        viz.plot_top_keywords(Path(stage_a_dir) / 'by_keyword.csv')
    except Exception as e:
        print(f"Error plotting top keywords: {e}")
    
    try:
        viz.plot_keyword_wordcloud(Path(stage_a_dir) / 'by_keyword.csv')
    except Exception as e:
        print(f"Error generating keyword wordcloud: {e}")
    
    try:
        viz.plot_language_distribution(Path(stage_a_dir) / 'by_language.csv')
    except Exception as e:
        print(f"Error plotting language distribution: {e}")
    
    try:
        viz.plot_stars_distribution(Path(stage_a_dir) / 'stars_distribution.csv')
    except Exception as e:
        print(f"Error plotting stars distribution: {e}")
    
    # Stage B charts
    try:
        viz.plot_filter_results(Path(stage_b_dir) / 'filter_by_keyword.csv')
    except Exception as e:
        print(f"Error plotting filter results: {e}")
    
    try:
        viz.plot_reason_length_comparison(Path(stage_b_dir) / 'reason_length_distribution.csv')
    except Exception as e:
        print(f"Error plotting reason length comparison: {e}")
    
    # Repo meta charts
    try:
        viz.plot_extension_distribution(Path(repo_meta_dir) / 'extension_distribution.csv', repo_top_n=top_n)
    except Exception as e:
        print(f"Error plotting extension distribution: {e}")
    
    try:
        viz.plot_repo_file_count_distribution(Path(repo_meta_dir) / f'repo_meta_scan{top_n_suffix}.csv', repo_top_n=top_n)
    except Exception as e:
        print(f"Error plotting repo file count distribution: {e}")
    
    # Code stats charts
    try:
        viz.plot_stars_vs_code_size(repos_searched_csv, Path(code_stats_dir) / f'repo_level_metrics{top_n_suffix}.csv', repo_top_n=top_n)
    except Exception as e:
        print(f"Error plotting stars vs code size: {e}")
    
    try:
        viz.plot_repo_stats_by_language(Path(code_stats_dir) / f'repo_level_metrics{top_n_suffix}.csv', repo_top_n=top_n)
    except Exception as e:
        print(f"Error plotting repo stats by language: {e}")
    
    print(f"Visualization complete! All figures saved to {viz.output_dir}")