Feat: Auto readme update with recent stats

.github/workflows/update.yml

@@ -46,6 +46,7 @@ jobs:
       - name: Run pythonAuto
         run: |
           poetry run python generate_database.py
+          poetry run python db_checker.py
 
       - name: Commit database changes
         run: |
@@ -54,6 +55,8 @@ jobs:
           if [[ ! -z $(git status -s) ]]; then
             git add database.json
             git commit -m "chore: update plugins database"
+            git add README.md
+            git commit -m "chore: update readme stats"
             git add dotfiles.json
             git commit -m "chore: update dotfiles database"
           fi

README.md

@@ -30,3 +30,14 @@ poetry init -> poetry install -> poetry run python ...
 # Key Notes
 
 Remember, Robert's doing his best out here in the wilds of GitHub. Treat him well, and he'll treat you to the finest collection of Neovim treasures the internet has to offer. 🎩🔍
+
+
+# Database Information
+
+<div style='display:flex;flex-direction:row;justify-content:space-between;'><table><tr><td><h3>Top 10 Plugins by Stars</h3><table border="1"><tr><th>Plugin</th><th>Stars</th></tr><tr><td>telescope.nvim</td><td>13298</td></tr><tr><td>lazy.nvim</td><td>10586</td></tr><tr><td>nvim-lspconfig</td><td>9167</td></tr><tr><td>packer.nvim</td><td>7499</td></tr><tr><td>nvim-cmp</td><td>6787</td></tr><tr><td>mason.nvim</td><td>6422</td></tr><tr><td>nvim-tree.lua</td><td>6290</td></tr><tr><td>neorg</td><td>5473</td></tr><tr><td>harpoon</td><td>5155</td></tr><tr><td>lualine.nvim</td><td>5096</td></tr></table></td><td><h3>Top 10 Plugins by Issues</h3><table border="1"><tr><th>Plugin</th><th>Issues</th></tr><tr><td>telescope.nvim</td><td>312</td></tr><tr><td>packer.nvim</td><td>305</td></tr><tr><td>nvim-cmp</td><td>223</td></tr><tr><td>lualine.nvim</td><td>187</td></tr><tr><td>which-key.nvim</td><td>183</td></tr><tr><td>neo-tree.nvim</td><td>172</td></tr><tr><td>neorg</td><td>153</td></tr><tr><td>mason.nvim</td><td>137</td></tr><tr><td>trouble.nvim</td><td>130</td></tr><tr><td>rust-tools.nvim</td><td>121</td></tr></table></td><td><h3>Top 10 Plugins by Forks</h3><table border="1"><tr><th>Plugin</th><th>Forks</th></tr><tr><td>nvim-lspconfig</td><td>1978</td></tr><tr><td>null-ls.nvim</td><td>802</td></tr><tr><td>telescope.nvim</td><td>748</td></tr><tr><td>nvim-tree.lua</td><td>589</td></tr><tr><td>lualine.nvim</td><td>431</td></tr><tr><td>nvim-cmp</td><td>339</td></tr><tr><td>tokyonight.nvim</td><td>321</td></tr><tr><td>harpoon</td><td>312</td></tr><tr><td>lspsaga.nvim</td><td>273</td></tr><tr><td>ChatGPT.nvim</td><td>264</td></tr></table></td></tr></table></div>
+
+### Final Stats
+- Total Plugins: 2425
+- Lua Plugins: 2425
+- Proportion of Lua Plugins (%): 100.00
+- Average Activity Score: 199.43

db_checker.py

@@ -5,6 +5,7 @@
 from rich.console import Console
 from rich.table import Table
 
+
 class DatabaseAnalyzer:
 
     def __init__(self, database_path='database.json', lengthA=10, lengthB=10):
@@ -37,8 +38,8 @@ def simplify_language_distribution(self):
         # Use get to safely access the count for each language, defaulting to 0 if not found
         # This approach avoids KeyError for languages not present in language_counts
         self.plugins_df['simplified_language'] = self.plugins_df[
-            'language'].apply(
-                lambda x: x if language_counts.get(x, 0) > 1 else 'Other')
+            'language'].apply(lambda x: x
+                              if language_counts.get(x, 0) > 1 else 'Other')
 
     def calculate_statistics(self):
         stats_df = self.plugins_df[[
@@ -61,26 +62,27 @@ def get_topics_distribution(self):
         return topics_series.head(self.lengthB)  # Only the top 5 topics
 
     def print_summary(self):
-        self.console.print(
-            f"Total plugins: {len(self.plugins_df)}", style="bold green")
-
-        stats_df = self.calculate_statistics()
-        self.console.print("\nStatistical Summary:", style="bold underline")
-        self.print_table(stats_df, ['Metric', 'Mean', 'Standard Deviation'])
-
-        lang_dist = self.get_language_distribution()
-        self.console.print("\nLanguage distribution:", style="bold underline")
-        self.print_table(lang_dist, ['Language', 'Count'])
-
-        avg_activity_score_by_lang = self.get_average_activity_score_by_language(
-        )
-        self.console.print(
-            "\nAverage Activity Score by Language:", style="bold underline")
-        self.print_table(
-            avg_activity_score_by_lang, ['Language', 'Average Activity Score'])
+        # self.console.print(
+        #     f"Total plugins: {len(self.plugins_df)}", style="bold green")
+        #
+        # stats_df = self.calculate_statistics()
+        # self.console.print("\nStatistical Summary:", style="bold underline")
+        # self.print_table(stats_df, ['Metric', 'Mean', 'Standard Deviation'])
+        #
+        # lang_dist = self.get_language_distribution()
+        # self.console.print("\nLanguage distribution:", style="bold underline")
+        # self.print_table(lang_dist, ['Language', 'Count'])
+
+        # avg_activity_score_by_lang = self.get_average_activity_score_by_language(
+        # )
+        # self.console.print("\nAverage Activity Score by Language:",
+        #                    style="bold underline")
+        # self.print_table(avg_activity_score_by_lang,
+        #                  ['Language', 'Average Activity Score'])
 
         topics_distribution = self.get_topics_distribution()
-        self.console.print("\nTop Topics distribution:", style="bold underline")
+        self.console.print("\nTop Topics distribution:",
+                           style="bold underline")
         self.print_table(topics_distribution, ['Topic', 'Count'])
 
     def print_table(self, data, columns):
@@ -104,9 +106,8 @@ def print_top_plugins(self):
         }
 
         for category, column_name in categories.items():
-            self.console.print(
-                f"\nTop {self.lengthA} Plugins by {category}:",
-                style="bold underline magenta")
+            self.console.print(f"\nTop {self.lengthA} Plugins by {category}:",
+                               style="bold underline magenta")
             top_plugins = self.plugins_df.nlargest(self.lengthA,
                                                    column_name)[[column_name]]
 
@@ -120,40 +121,110 @@ def print_top_plugins(self):
             self.console.print(table)
 
         total_plugins = len(self.plugins_df)
-        lua_plugins = len(self.plugins_df[self.plugins_df['language'] == 'Lua'])
-        proportion_lua = (lua_plugins/total_plugins) * 100
+        lua_plugins = len(
+            self.plugins_df[self.plugins_df['language'] == 'Lua'])
+        proportion_lua = (lua_plugins / total_plugins) * 100
         average_activity_score = self.plugins_df['activity_score'].mean()
 
         table = Table(show_header=True, header_style="bold magenta")
         table.add_column("Total Plugins", style="dim", justify="right")
         table.add_column("Lua Plugins", style="dim", justify="right")
-        table.add_column(
-            "Proportion of Lua Plugins (%)", style="dim", justify="right")
-        table.add_column("Average Activity Score", style="dim", justify="right")
+        table.add_column("Proportion of Lua Plugins (%)",
+                         style="dim",
+                         justify="right")
+        table.add_column("Average Activity Score",
+                         style="dim",
+                         justify="right")
 
-        table.add_row(
-            str(total_plugins), str(lua_plugins), f"{proportion_lua:.2f}",
-            f"{average_activity_score:.2f}")
+        table.add_row(str(total_plugins), str(lua_plugins),
+                      f"{proportion_lua:.2f}", f"{average_activity_score:.2f}")
 
         self.console.print(table)
 
+    def generate_markdown_table(self, data, columns):
+        markdown_table = "| " + " | ".join(columns) + " |\n"
+        markdown_table += "| " + " | ".join(['---'] * len(columns)) + " |\n"
+        if isinstance(data, pd.Series):
+            for index, value in data.items():
+                markdown_table += "| " + " | ".join([str(index),
+                                                     str(value)]) + " |\n"
+        else:
+            for index, row in data.iterrows():
+                markdown_table += "| " + index + " | " + f"{row['mean']:.2f}" + " | " + f"{row['std']:.2f}" + " |\n"
+        return markdown_table
+
+    def save_to_markdown(self):
+        new_content = ""
+        categories = {
+            "Stars": "stargazers_count",
+            "Issues": "open_issues_count",
+            "Forks": "forks_count"
+        }
+
+        # Generate HTML for the top plugins in each category
+        plugins_html = self.generate_html_for_plugins(categories)
+        new_content += "<div style='display:flex;flex-direction:row;justify-content:space-between;'>" + plugins_html + "</div>\n\n"
+
+        # Final stats in Markdown
+        total_plugins = len(self.plugins_df)
+        lua_plugins = len(
+            self.plugins_df[self.plugins_df['language'] == 'Lua'])
+        proportion_lua = (lua_plugins / total_plugins) * 100
+        average_activity_score = self.plugins_df['activity_score'].mean()
+        new_content += "### Final Stats\n"
+        new_content += f"- Total Plugins: {total_plugins}\n"
+        new_content += f"- Lua Plugins: {lua_plugins}\n"
+        new_content += f"- Proportion of Lua Plugins (%): {proportion_lua:.2f}\n"
+        new_content += f"- Average Activity Score: {average_activity_score:.2f}\n"
+
+        # Read and split the existing README
+        try:
+            with open("README.md", "r+") as md_file:
+                content = md_file.read()
+                parts = content.split("# Database Information", 1)
+                updated_content = parts[
+                    0] + "# Database Information\n\n" + new_content
+                md_file.seek(0)
+                md_file.write(updated_content)
+                md_file.truncate()
+        except FileNotFoundError:
+            with open("README.md", "w") as md_file:
+                md_file.write("# Database Information\n\n" + new_content)
+
+    def generate_html_for_plugins(self, categories):
+        html_content = '<table><tr>'
+        for category, column_name in categories.items():
+            top_plugins = self.plugins_df.nlargest(self.lengthA,
+                                                   column_name)[[column_name]]
+            html_content += '<td><h3>Top 10 Plugins by ' + category + '</h3>'
+            html_content += '<table border="1"><tr><th>Plugin</th><th>' + category + '</th></tr>'
+            for plugin_name, row in top_plugins.iterrows():
+                html_content += '<tr><td>' + plugin_name + '</td><td>' + str(
+                    row[column_name]) + '</td></tr>'
+            html_content += '</table></td>'
+        html_content += '</tr></table>'
+        return html_content
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Check the database')
-    parser.add_argument(
-        '--db',
-        help='Path to the database file',
-        default='database.json',
-        type=str)
-    parser.add_argument(
-        "--lenA", help="Length of items you want to view", default=10, type=int)
-    parser.add_argument(
-        "--lenB",
-        help="Length of Topic Distribution you want to view",
-        default=15,
-        type=int)
+    parser.add_argument('--db',
+                        help='Path to the database file',
+                        default='database.json',
+                        type=str)
+    parser.add_argument("--lenA",
+                        help="Length of items you want to view",
+                        default=10,
+                        type=int)
+    parser.add_argument("--lenB",
+                        help="Length of Topic Distribution you want to view",
+                        default=10,
+                        type=int)
 
     args = parser.parse_args()
-    analyzer = DatabaseAnalyzer(
-        database_path=args.db, lengthA=args.lenA, lengthB=args.lenB)
-    analyzer.print_summary()
-    analyzer.print_top_plugins()
+    analyzer = DatabaseAnalyzer(database_path=args.db,
+                                lengthA=args.lenA,
+                                lengthB=args.lenB)
+    # analyzer.print_summary()
+    # analyzer.print_top_plugins()
+    analyzer.save_to_markdown()

test.py

@@ -527,12 +527,10 @@ def make_jobs(base) -> None:
     def name_function(x, y):
         return any(x.lower().startswith(ig.lower()) for ig in y)
 
-
-    fixed_plugin_conds = [
-    ]
+    fixed_plugin_conds = []
     fixed_dotfile_conds = [
         fullname_mapper(
-            lambda x, y: y.lower() in x.lower(),unwanted_config
+            lambda x, y: y.lower() in x.lower(), unwanted_config
         ),  # checks if any of the unwanted config names are in d['full_name']
         description_mapper(
             lambda x,
@@ -541,30 +539,19 @@ def name_function(x, y):
         ),  # check if any of the unwanted config names are in d['description']
     ]
     both_conditions = [
-        language_mapper(
-            lambda x, y: x.lower() == "lua", ["lua"]
-        )
+        language_mapper(lambda x, y: x.lower() == "lua", ["lua"])
     ]
 
-    optional_plugin_conds = [
-        ends_nvim,
-
+    optional_plugin_conds = [ends_nvim,]
+    optional_dotfile_conds = [begins_dot,]
 
-    ]
-    optional_dotfile_conds = [
-        begins_dot,
-    ]
-
-    conds = (fixed_plugin_conds,fixed_dotfile_conds)
+    conds = (fixed_plugin_conds, fixed_dotfile_conds)
     cases = {
         # mappings for conditions based on conditions
         (1, 0): "plugin_count",
         (0, 1): "dotfile_count",
     }
 
-
-
-
     def make_jobtype(response):
         plugin_data = response
         # case = tuple(min(1, sum(cn(plugin_data) for cn in c)) for c in conds)