ASF Analysis: Heat Pump Efficiency and Green Finance Notebooks #7
Conversation
- Added CB_hp_efficiency.ipynb and gtr_lch_efficiency_search.ipynb for heat pump efficiency analysis - Added CB_LC_green_finance_search.ipynb and gtr_green_finance_search.ipynb for green finance analysis - Enhanced notebooks with time series imputation and Google Sheets integration - Updated .gitignore to exclude generated outputs (CSVs, PNGs, HTML) 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
There was a problem hiding this comment.
Pull Request Overview
This PR adds comprehensive analysis notebooks for the ASF mission focusing on affordability and efficiency in heating solutions through four Jupyter notebooks covering heat pump efficiency research and green finance analysis.
Key changes:
- Implements dual-stage filtering approach for green finance research (broad green finance → low-carbon heating specific)
- Adds LLM-validated analysis for heat pump efficiency research projects
- Standardizes notebook structure across both Crunchbase (CB) and Gateway to Research (GTR) data sources
Reviewed Changes
Copilot reviewed 8 out of 11 changed files in this pull request and generated 5 comments.
| File | Description |
|---|---|
| gtr_green_finance_search.ipynb | Two-stage GTR analysis notebook with progressive filtering and comprehensive documentation |
| gtr_lch_efficiency_search.ipynb | GTR heat pump efficiency analysis with simplified directory structure and chart generation |
| config files (*.yaml) | Search configuration files defining keywords and scope statements for both CB and GTR analyses |
| " except Exception as e:\n", | ||
| " print(f\"❌ Error uploading {config_name} to Google Sheets: {e}\")\n", | ||
| "\n", | ||
| "print(\"\\\\n🎯 Main data Google Sheets upload complete!\")" |
There was a problem hiding this comment.
The string contains an escaped backslash that will be printed literally as '\n' instead of a newline. Remove one backslash to fix: print("\n🎯 Main data Google Sheets upload complete!")
| "print(\"\\\\n🎯 Main data Google Sheets upload complete!\")" | |
| "print(\"\\n🎯 Main data Google Sheets upload complete!\")" |
Copilot uses AI. Check for mistakes.
| " import traceback\n", | ||
| " traceback.print_exc()\n", | ||
| "\n", | ||
| "print(\"\\\\n🎯 Chart data Google Sheets upload complete!\")" |
There was a problem hiding this comment.
The string contains an escaped backslash that will be printed literally as '\n' instead of a newline. Remove one backslash to fix: print("\n🎯 Chart data Google Sheets upload complete!")
| "print(\"\\\\n🎯 Chart data Google Sheets upload complete!\")" | |
| "print(\"\\n🎯 Chart data Google Sheets upload complete!\")" |
Copilot uses AI. Check for mistakes.
| "from pathlib import Path\n", | ||
| "#from discovery_mission_radar import VECTOR_DB_DIR" |
There was a problem hiding this comment.
Remove commented-out import that is not needed. The VECTOR_DB_DIR is created locally within the notebook.
| "from pathlib import Path\n", | |
| "#from discovery_mission_radar import VECTOR_DB_DIR" | |
| "from pathlib import Path\n" |
Copilot uses AI. Check for mistakes.
| " session_name=\"mission_studio\",\n", | ||
| " output_fields=[{\"name\":\"is_relevant\",\"type\":\"str\",\"description\":\"yes or no\"}]\n", | ||
| " )\n", | ||
| " await proc1.run(dict(zip(relevant_gf['id'], relevant_gf['abstractText'])), batch_size=15, sleep_time=0.5)\n", |
There was a problem hiding this comment.
[nitpick] Consider extracting the batch_size and sleep_time as configurable constants at the top of the notebook to make it easier to adjust LLM processing parameters without searching through the code.
| " await proc1.run(dict(zip(relevant_gf['id'], relevant_gf['abstractText'])), batch_size=15, sleep_time=0.5)\n", | |
| " await proc1.run(dict(zip(relevant_gf['id'], relevant_gf['abstractText'])), batch_size=BATCH_SIZE, sleep_time=SLEEP_TIME)\n", |
Copilot uses AI. Check for mistakes.
| " session_name='mission_studio',\n", | ||
| " output_fields=[{'name':'is_relevant','type':'str','description':'yes or no'}]\n", | ||
| " )\n", | ||
| " await processor.run(dict(zip(relevant['id'], relevant['abstractText'])), batch_size=15, sleep_time=0.5)\n", |
There was a problem hiding this comment.
[nitpick] Consider extracting the batch_size and sleep_time as configurable constants at the top of the notebook to make it easier to adjust LLM processing parameters without searching through the code.
| " await processor.run(dict(zip(relevant['id'], relevant['abstractText'])), batch_size=15, sleep_time=0.5)\n", | |
| " await processor.run(dict(zip(relevant['id'], relevant['abstractText'])), batch_size=BATCH_SIZE, sleep_time=SLEEP_TIME)\n", |
Copilot uses AI. Check for mistakes.
Add comprehensive GtR analysis notebook for low-carbon heating (LCH) optimisation research projects including data extraction, filtering, and relevance checking workflows. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Summary
Added comprehensive analysis notebooks for ASF mission focusing on affordability and efficiency in heating solutions.
Notebooks Added
Key Features
Technical Improvements
Review Instructions
Next Steps
🤖 Generated with Claude Code