scholarimpact 0.0.1.dev1__tar.gz → 0.0.2.dev2__tar.gz

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/.gitignore

@@ -207,7 +207,7 @@ example-dashboard
 my-research-dashboard
 .DS_Store
 .claude
-data
+data/8/json
 
 # setuptools-scm generated version file
 src/scholarimpact/_version.py

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scholarimpact
-Version: 0.0.1.dev1
+Version: 0.0.2.dev2
 Summary: A bibliometric tool to analyse, visualise, and share your research impact, output and scholarly influence using Google Scholar and OpenAlex data
 Author-email: Abhishek Tiwari <scholarimpact@abhishek-tiwari.com>
 License: MIT
@@ -53,9 +53,9 @@ A bibliometric tool to analyse, visualise, and share your research impact, outpu
 
 For each article under your Google Scholar Profile, **_ScholarImpact_**: (1) total number of citations, (2) number of unique authors who have cited the article, (3) number of countries from which citations originate, (4) number of institutions from which citations originate, (5) geographic distribution of citations, (6) citation trends over time, (7) research domain analysis, (8) interdisciplinary impact Metrics including Patents and Wikipedia mentions.
 
-![Example Dashboard](example-dashboard.png)
+![Example Dashboard](https://static.abhishek-tiwari.com/scholarimpact/example-dashboard.png)
 
-![Research Domains Analysis](research-domains.png)
+![Research Domains Analysis](https://static.abhishek-tiwari.com/scholarimpact/research-domains.png)
 
 ## Workflow Overview
 This workflow extracts author data from your Google Scholar profile, then crawls citations for each article under your Google Scholar profile. Next workflow enriches them with information using Google Scholar profiles of citing authors and OpenAlex APIs. Finally, output data is used to present your impact of your research with geographic and institutional insights.

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/README.md

@@ -3,9 +3,9 @@ A bibliometric tool to analyse, visualise, and share your research impact, outpu
 
 For each article under your Google Scholar Profile, **_ScholarImpact_**: (1) total number of citations, (2) number of unique authors who have cited the article, (3) number of countries from which citations originate, (4) number of institutions from which citations originate, (5) geographic distribution of citations, (6) citation trends over time, (7) research domain analysis, (8) interdisciplinary impact Metrics including Patents and Wikipedia mentions.
 
-![Example Dashboard](example-dashboard.png)
+![Example Dashboard](https://static.abhishek-tiwari.com/scholarimpact/example-dashboard.png)
 
-![Research Domains Analysis](research-domains.png)
+![Research Domains Analysis](https://static.abhishek-tiwari.com/scholarimpact/research-domains.png)
 
 ## Workflow Overview
 This workflow extracts author data from your Google Scholar profile, then crawls citations for each article under your Google Scholar profile. Next workflow enriches them with information using Google Scholar profiles of citing authors and OpenAlex APIs. Finally, output data is used to present your impact of your research with geographic and institutional insights.

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/src/scholarimpact/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.1.dev1'
-__version_tuple__ = version_tuple = (0, 0, 1, 'dev1')
+__version__ = version = '0.0.2.dev2'
+__version_tuple__ = version_tuple = (0, 0, 2, 'dev2')

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/src/scholarimpact/dashboard/app.py

@@ -96,6 +96,18 @@ class Dashboard:
             port: Port to run dashboard on (optional, uses instance port)
             debug: Enable debug mode
         """
+        # Check if we're already running in Streamlit context
+        try:
+            import streamlit as st
+            # If we can access Streamlit's runtime, we're already in a Streamlit app
+            if hasattr(st, 'runtime') and st.runtime.exists():
+                # Just render directly, no subprocess needed
+                self.render_app()
+                return
+        except:
+            # Not in Streamlit context or error checking, proceed with subprocess
+            pass
+
         if port is None:
             port = self.port
 

scholarimpact-0.0.2.dev2/src/scholarimpact/data/__init__.py

@@ -0,0 +1,5 @@
+"""Data module for ScholarImpact."""
+
+from .loader import load_data
+
+__all__ = ['load_data']

scholarimpact-0.0.2.dev2/src/scholarimpact/data/loader.py

@@ -0,0 +1,131 @@
+"""
+Data loading utilities for ScholarImpact.
+"""
+
+import json
+import logging
+import os
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+import pandas as pd
+
+logger = logging.getLogger(__name__)
+
+def load_data(data_dir: str = 'data') -> Dict[str, Any]:
+    """
+    Load citation data from the data directory.
+    
+    Args:
+        data_dir: Directory containing the data files
+        
+    Returns:
+        Dictionary containing loaded data
+    """
+    data = {}
+    data_path = Path(data_dir)
+    
+    if not data_path.exists():
+        logger.warning(f"Data directory {data_dir} does not exist")
+        return data
+    
+    # Load author.json
+    author_file = data_path / 'author.json'
+    if author_file.exists():
+        try:
+            with open(author_file, 'r', encoding='utf-8') as f:
+                data['author'] = json.load(f)
+                
+                # Extract articles if present
+                if 'articles' in data['author']:
+                    data['articles'] = pd.DataFrame(data['author']['articles'])
+                    
+            logger.info(f"Loaded author data from {author_file}")
+        except Exception as e:
+            logger.error(f"Error loading author data: {e}")
+    
+    # Load citation files
+    citation_files = list(data_path.glob('cites-*.json'))
+    if citation_files:
+        data['citation_files'] = {}
+        for citation_file in citation_files:
+            try:
+                with open(citation_file, 'r', encoding='utf-8') as f:
+                    citations = json.load(f)
+                    # Extract cites_id from filename
+                    cites_id = citation_file.stem.replace('cites-', '')
+                    data['citation_files'][cites_id] = citations
+                    
+            except Exception as e:
+                logger.warning(f"Error loading {citation_file}: {e}")
+        
+        logger.info(f"Loaded {len(data['citation_files'])} citation files")
+    
+    # Process and enhance articles data if available
+    if 'articles' in data and not data['articles'].empty:
+        data['articles'] = enhance_articles_data(data['articles'], data.get('citation_files', {}))
+    
+    return data
+
+def enhance_articles_data(articles_df: pd.DataFrame, citation_files: Dict[str, Any]) -> pd.DataFrame:
+    """
+    Enhance articles data with citation analysis.
+    
+    Args:
+        articles_df: DataFrame containing article data
+        citation_files: Dictionary of citation files
+        
+    Returns:
+        Enhanced DataFrame
+    """
+    # Initialize new columns
+    articles_df['crawler_data_available'] = False
+    articles_df['unique_citing_authors'] = 0
+    articles_df['unique_countries'] = 0
+    articles_df['unique_institutions'] = 0
+    
+    for idx, row in articles_df.iterrows():
+        cites_id = row.get('cites_id', '')
+        if not cites_id:
+            continue
+        
+        # Handle multiple IDs
+        if ',' in str(cites_id):
+            file_cites_id = str(cites_id).replace(',', '_')
+        else:
+            file_cites_id = str(cites_id)
+        
+        # Check if we have citation data
+        if file_cites_id in citation_files:
+            articles_df.at[idx, 'crawler_data_available'] = True
+            citations = citation_files[file_cites_id]
+            
+            # Count unique citing authors
+            citing_authors = set()
+            countries = set()
+            institutions = set()
+            
+            for citation in citations:
+                # Extract authors
+                if 'citing_authors' in citation:
+                    authors = citation['citing_authors'].split(',')
+                    for author in authors:
+                        author = author.strip()
+                        if author and author != 'Unknown':
+                            citing_authors.add(author)
+                
+                # Extract countries and institutions from author details
+                for author_detail in citation.get('citing_authors_details', []):
+                    country = author_detail.get('country', '')
+                    if country and country not in ['Unknown', '']:
+                        countries.add(country)
+                    
+                    institution = author_detail.get('institution_display_name', '')
+                    if institution and institution not in ['Unknown', '']:
+                        institutions.add(institution)
+            
+            articles_df.at[idx, 'unique_citing_authors'] = len(citing_authors)
+            articles_df.at[idx, 'unique_countries'] = len(countries)
+            articles_df.at[idx, 'unique_institutions'] = len(institutions)
+    
+    return articles_df

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/src/scholarimpact.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scholarimpact
-Version: 0.0.1.dev1
+Version: 0.0.2.dev2
 Summary: A bibliometric tool to analyse, visualise, and share your research impact, output and scholarly influence using Google Scholar and OpenAlex data
 Author-email: Abhishek Tiwari <scholarimpact@abhishek-tiwari.com>
 License: MIT
@@ -53,9 +53,9 @@ A bibliometric tool to analyse, visualise, and share your research impact, outpu
 
 For each article under your Google Scholar Profile, **_ScholarImpact_**: (1) total number of citations, (2) number of unique authors who have cited the article, (3) number of countries from which citations originate, (4) number of institutions from which citations originate, (5) geographic distribution of citations, (6) citation trends over time, (7) research domain analysis, (8) interdisciplinary impact Metrics including Patents and Wikipedia mentions.
 
-![Example Dashboard](example-dashboard.png)
+![Example Dashboard](https://static.abhishek-tiwari.com/scholarimpact/example-dashboard.png)
 
-![Research Domains Analysis](research-domains.png)
+![Research Domains Analysis](https://static.abhishek-tiwari.com/scholarimpact/research-domains.png)
 
 ## Workflow Overview
 This workflow extracts author data from your Google Scholar profile, then crawls citations for each article under your Google Scholar profile. Next workflow enriches them with information using Google Scholar profiles of citing authors and OpenAlex APIs. Finally, output data is used to present your impact of your research with geographic and institutional insights.

{scholarimpact-0.0.1.dev1 → scholarimpact-0.0.2.dev2}/src/scholarimpact.egg-info/SOURCES.txt

@@ -3,11 +3,9 @@ CITATION.cff
 LICENSE
 Makefile
 README.md
-example-dashboard.png
 pyproject.toml
 requirements-dev.txt
 requirements.txt
-research-domains.png
 .github/workflows/cleanup-prereleases.yml
 .github/workflows/release.yml
 .github/workflows/test.yml
@@ -48,5 +46,7 @@ src/scholarimpact/dashboard/components/base.py
 src/scholarimpact/dashboard/components/config.py
 src/scholarimpact/dashboard/components/layout.py
 src/scholarimpact/dashboard/components/streamlit_app.py
+src/scholarimpact/data/__init__.py
+src/scholarimpact/data/loader.py
 tests/.gitkeep
 tests/test_basic.py