1
0
govdoc-cr-analysis/text_analysis/readme_partitioned_analysis.ipynb

70 lines
1.5 KiB
Plaintext
Raw Normal View History

2025-02-03 17:57:20 +00:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"merged_manifest = pd.read_csv('0203_readme_merged_manifest.csv')\n",
"topic_distributions = pd.read_csv('020125_README_file_topic_distributions.csv')\n",
"readability_scores = pd.read_csv('020125_README_readability.csv')"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4248"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"first_merge = readability_scores.merge(topic_distributions, on=['filename'],how=\"inner\")\n",
"#primary_merge = first_merge.merge(readability_scores, )\n",
"first_merge['fvf_filepath'] = first_merge['filename']\n",
"second_merge = first_merge.merge(merged_manifest, on=['fvf_filepath'], how=\"inner\")\n",
"len(second_merge)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}