From e0316f4106f6be82e8471303a6d5f659336cee5e Mon Sep 17 00:00:00 2001
From: Adrienucl <adrien.payen@student.uclouvain.be>
Date: Mon, 8 Apr 2024 14:50:34 +0200
Subject: [PATCH] =?UTF-8?q?commit=20de=20fin=20de=20r=C3=A9union?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
Analytics_UI/analytics.ipynb | 25 ++-
.../{analytics.py => analytics_small.py} | 9 +-
Analytics_UI/analytics_tiny.py | 151 ++++++++++++++++++
Analytics_UI/constants.py | 2 +-
Analytics_UI/matrice.py | 0
5 files changed, 177 insertions(+), 10 deletions(-)
rename Analytics_UI/{analytics.py => analytics_small.py} (95%)
create mode 100644 Analytics_UI/analytics_tiny.py
create mode 100644 Analytics_UI/matrice.py
diff --git a/Analytics_UI/analytics.ipynb b/Analytics_UI/analytics.ipynb
index 9cfe0519..dd9c2e8d 100644
--- a/Analytics_UI/analytics.ipynb
+++ b/Analytics_UI/analytics.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 1,
"metadata": {},
"outputs": [
{
@@ -21,7 +21,7 @@
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[12], line 10\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mre\u001b[39;00m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mconstants\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Constant \u001b[38;5;28;01mas\u001b[39;00m C\n\u001b[0;32m---> 10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mloaders\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_ratings\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mloaders\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_items\n\u001b[1;32m 13\u001b[0m load_items()\n",
+ "Cell \u001b[0;32mIn[1], line 10\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mre\u001b[39;00m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mconstants\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Constant \u001b[38;5;28;01mas\u001b[39;00m C\n\u001b[0;32m---> 10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mloaders\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_ratings\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mloaders\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_items\n\u001b[1;32m 13\u001b[0m load_items()\n",
"File \u001b[0;32m~/vscodeworkspace/recomsys/Analytics_UI/loaders.py:41\u001b[0m\n\u001b[1;32m 39\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 40\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDisplay the ratings\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 41\u001b[0m pp(\u001b[43mload_ratings\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 42\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 43\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDisplay the movie data\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m~/vscodeworkspace/recomsys/Analytics_UI/loaders.py:12\u001b[0m, in \u001b[0;36mload_ratings\u001b[0;34m(surprise_format)\u001b[0m\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_ratings\u001b[39m(surprise_format\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m---> 12\u001b[0m df_ratings \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mC\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mEVIDENCE_PATH\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m/\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mC\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mRATINGS_FILENAME\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m surprise_format:\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n",
"File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:948\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 935\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 936\u001b[0m dialect,\n\u001b[1;32m 937\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 944\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 945\u001b[0m )\n\u001b[1;32m 946\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m--> 948\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
@@ -121,9 +121,26 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "FileNotFoundError",
+ "evalue": "[Errno 2] No such file or directory: 'data/small/evidence/ratings.csv'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[2], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# THE TOTAL NUMBER OF RATINGS\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df_ratings \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata/small/evidence/ratings.csv\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m n_ratings \u001b[38;5;241m=\u001b[39m df_ratings[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrating\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mcount()\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of ratings: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mn_ratings\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+ "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:948\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 935\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 936\u001b[0m dialect,\n\u001b[1;32m 937\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 944\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 945\u001b[0m )\n\u001b[1;32m 946\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m--> 948\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:611\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 608\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m 610\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 611\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 613\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m 614\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
+ "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1448\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1445\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1447\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1448\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1705\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1703\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[1;32m 1704\u001b[0m mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 1705\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1706\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1707\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1708\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1709\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1710\u001b[0m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1711\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1712\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1713\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1714\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1715\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1716\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
+ "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/common.py:863\u001b[0m, in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 858\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 859\u001b[0m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[1;32m 860\u001b[0m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[1;32m 861\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[1;32m 862\u001b[0m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[0;32m--> 863\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 864\u001b[0m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 865\u001b[0m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 866\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 867\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 868\u001b[0m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 869\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 870\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 871\u001b[0m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[1;32m 872\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
+ "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'data/small/evidence/ratings.csv'"
+ ]
+ }
+ ],
"source": [
"# THE TOTAL NUMBER OF RATINGS\n",
"df_ratings = pd.read_csv(\"data/small/evidence/ratings.csv\")\n",
diff --git a/Analytics_UI/analytics.py b/Analytics_UI/analytics_small.py
similarity index 95%
rename from Analytics_UI/analytics.py
rename to Analytics_UI/analytics_small.py
index 7aa68d0d..8f9fe665 100644
--- a/Analytics_UI/analytics.py
+++ b/Analytics_UI/analytics_small.py
@@ -60,7 +60,10 @@ print(f"Number of users: {n_users}")
print("\n","C")
-
+df_ratings = pd.read_csv("data/small/evidence/ratings.csv")
+unique_movies = df_ratings["movieId"].unique()
+num_unique_movies = len(unique_movies)
+print("Number of unique movies : ", num_unique_movies)
print("\n","D")
def most_rated_movies_ratings_count(csv_file):
@@ -136,10 +139,6 @@ unrated_movies_count("data/small/evidence/ratings.csv", "data/small/content/movi
-
-
-
-
# -- display relevant informations that can be extracted from the dataset
diff --git a/Analytics_UI/analytics_tiny.py b/Analytics_UI/analytics_tiny.py
new file mode 100644
index 00000000..32b1f323
--- /dev/null
+++ b/Analytics_UI/analytics_tiny.py
@@ -0,0 +1,151 @@
+#reloads modules automatically before entering the execution of code
+# %load_ext autoreload
+# %autoreload 2
+
+# third parties imports
+import numpy as np
+import pandas as pd
+import re
+# -- add new imports here --
+
+# local imports
+from constants import Constant as C
+from loaders import load_ratings
+from loaders import load_items
+
+# -- load the items and display the Dataframe
+load_items()
+load_ratings()
+
+df_movies = pd.read_csv("data/tiny/content/movies.csv")
+n_movies = df_movies['title'].nunique()
+
+print("\n")
+print(f"Number of movies: {n_movies}")
+
+df_movies['annee'] = df_movies['title'].str.extract(r'\((.{4})\)')
+df_movies['annee'] = pd.to_numeric(df_movies['annee'], errors='coerce')
+
+# Trouver le range minimum et maximum
+min_range = int(df_movies['annee'].min())
+max_range = int(df_movies['annee'].max())
+
+# Afficher le range minimum et maximum
+print("\n")
+print(f"Minimum range: {min_range}")
+print(f"Maximum range: {max_range}")
+
+
+print("\n")
+df_movies['genres'] = df_movies['genres'].str.split('|')
+df_movies = df_movies.explode('genres')
+
+# Afficher tous les genres uniques
+unique_genres = sorted(df_movies['genres'].unique())
+print("List of all genres:")
+for genre in unique_genres:
+ print(genre, "|", end = " ")
+
+
+print("\n","A")
+df_ratings = pd.read_csv("data/tiny/evidence/ratings.csv")
+n_ratings = df_ratings['rating'].count()
+print(f"Number of ratings: {n_ratings}")
+
+
+print("\n","B")
+df_ratings = pd.read_csv("data/tiny/evidence/ratings.csv")
+n_users = df_ratings['userId'].nunique()
+print(f"Number of users: {n_users}")
+
+
+print("\n","C")
+df_ratings = pd.read_csv("data/tiny/evidence/ratings.csv")
+unique_movies = df_ratings["movieId"].unique()
+num_unique_movies = len(unique_movies)
+print("Number of unique movies : ", num_unique_movies)
+
+print("\n","D")
+def most_rated_movies_ratings_count(csv_file):
+ # Charger le DataFrame des évaluations à partir du fichier CSV
+ df_ratings = pd.read_csv(csv_file)
+
+ # Grouper les évaluations par 'movieId' et compter le nombre de notes pour chaque film
+ movie_ratings_count = df_ratings.groupby('movieId')['rating'].count()
+
+ # Trouver le(s) film(s) le(s) plus évalué(s)
+ most_rated_movies = movie_ratings_count[movie_ratings_count == movie_ratings_count.max()]
+
+ # Afficher le nombre de notes du film (ou des films) le(s) plus évalué(s)
+ print("Number of ratings of the most rated movie(s):", most_rated_movies.max())
+
+# Exemple d'utilisation de la fonction avec le chemin du fichier CSV
+most_rated_movies_ratings_count("data/tiny/evidence/ratings.csv")
+
+
+
+
+print("\n","E")
+def least_rated_movies_ratings_count(csv_file):
+ # Charger le DataFrame des évaluations à partir du fichier CSV
+ df_ratings = pd.read_csv(csv_file)
+
+ # Grouper les évaluations par 'movieId' et compter le nombre de notes pour chaque film
+ movie_ratings_count = df_ratings.groupby('movieId')['rating'].count()
+
+ # Trouver le(s) film(s) le(s) moins évalué(s)
+ least_rated_movies = movie_ratings_count[movie_ratings_count == movie_ratings_count.min()]
+
+ # Afficher le nombre de notes du film (ou des films) le(s) moins évalué(s)
+ print("Number of ratings of the least rated movie(s):", least_rated_movies.min())
+
+# Exemple d'utilisation de la fonction avec le chemin du fichier CSV
+least_rated_movies_ratings_count("data/tiny/evidence/ratings.csv")
+
+
+print("\n","F")
+def all_possible_ratings(csv_file):
+ # Charger le DataFrame des évaluations à partir du fichier CSV
+ df_ratings = pd.read_csv(csv_file)
+
+ # Obtenir toutes les valeurs de notation uniques
+ rating_values = sorted(df_ratings['rating'].unique())
+
+ # Afficher toutes les valeurs de notation possibles
+ print("All possible rating values, from smallest to highest:")
+ for rating in rating_values:
+ print(rating)
+
+# Exemple d'utilisation de la fonction avec le chemin du fichier CSV
+all_possible_ratings("data/tiny/evidence/ratings.csv")
+
+print("\n","G")
+def unrated_movies_count(ratings_csv, movies_csv):
+ # Charger les DataFrames des évaluations et des films à partir des fichiers CSV
+ df_ratings = pd.read_csv(ratings_csv)
+ df_movies = pd.read_csv(movies_csv)
+
+ # Obtenir la liste de tous les films présents dans le fichier de notation
+ rated_movies = df_ratings['movieId'].unique()
+
+ # Comparer la liste des films notés à la liste complète des films pour obtenir les films non notés
+ unrated_movies_count = df_movies[~df_movies['movieId'].isin(rated_movies)].shape[0]
+
+ # Afficher le nombre de films non notés
+ print("Number of movies that were not rated at all:", unrated_movies_count)
+
+# Exemple d'utilisation de la fonction avec les chemins des fichiers CSV des évaluations et des films
+unrated_movies_count("data/tiny/evidence/ratings.csv", "data/tiny/content/movies.csv")
+
+
+
+# -- display relevant informations that can be extracted from the dataset
+
+
+
+
+
+# -- load the items and display the Dataframe
+
+
+# -- display relevant informations that can be extracted from the dataset
diff --git a/Analytics_UI/constants.py b/Analytics_UI/constants.py
index ffb8239c..64947204 100644
--- a/Analytics_UI/constants.py
+++ b/Analytics_UI/constants.py
@@ -24,5 +24,5 @@ class Constant:
USER_ITEM_RATINGS = [USER_ID_COL, ITEM_ID_COL, RATING_COL]
# Rating scale
- RATINGS_SCALE = (0.0, 5.0) # -- fill in here the ratings scale as a tuple (min_value, max_value)
+ RATINGS_SCALE = (0.5, 5.0) # -- fill in here the ratings scale as a tuple (min_value, max_value)
# avant c 'était None
diff --git a/Analytics_UI/matrice.py b/Analytics_UI/matrice.py
new file mode 100644
index 00000000..e69de29b
--
GitLab