diff --git a/2_Evaluator_Block/configs.py b/2_Evaluator_Block/configs.py
index d58a423f80b87f1c73f5344237d18a6c1175abce..c0a0002c921ae0d97bf1206549529f3ea8821f17 100644
--- a/2_Evaluator_Block/configs.py
+++ b/2_Evaluator_Block/configs.py
@@ -26,7 +26,7 @@ class EvalConfig:
full_metrics = ["novelty"]
# Split parameters
- test_size = 0.3 # -- configure the test_size (from 0 to 1) --
+ test_size = 0.25 # -- configure the test_size (from 0 to 1) --
# Loo parameters
top_n_value = 10 # -- configure the numer of recommendations (> 1) --
diff --git a/2_Evaluator_Block/constants.py b/2_Evaluator_Block/constants.py
index e91304ece888415e93b8ee38f016b797acf8b4fc..6d18220868d9259d25f2b63770a2bac9b78ded36 100644
--- a/2_Evaluator_Block/constants.py
+++ b/2_Evaluator_Block/constants.py
@@ -6,7 +6,7 @@ class Constant:
"""Constants for dataset paths and column names."""
- DATA_PATH = Path('../data/small') # -- fill here the dataset size to use
+ DATA_PATH = Path('../data/tiny') # -- fill here the dataset size to use
# Content
CONTENT_PATH = DATA_PATH / 'content' # Path to content data
diff --git a/2_Evaluator_Block/evaluator.ipynb b/2_Evaluator_Block/evaluator.ipynb
index 017f1cae5a4c7eabf3b3b606a6081aca510dd441..f014373a6924ee31f7d63ac4b6fe11f77ea1d09d 100644
--- a/2_Evaluator_Block/evaluator.ipynb
+++ b/2_Evaluator_Block/evaluator.ipynb
@@ -13,7 +13,7 @@
},
{
"cell_type": "code",
- "execution_count": 182,
+ "execution_count": 58,
"id": "6aaf9140",
"metadata": {},
"outputs": [
@@ -59,7 +59,7 @@
},
{
"cell_type": "code",
- "execution_count": 183,
+ "execution_count": 59,
"id": "d6d82188",
"metadata": {},
"outputs": [],
@@ -74,8 +74,6 @@
" algo.fit(trainset)\n",
" # Predict ratings for the testset\n",
" predictions = algo.test(testset)\n",
- "\n",
- "\n",
" return predictions\n",
"\n",
"\n",
@@ -84,7 +82,7 @@
" # -- implement the function generate_loo_top_n --\n",
" # Create a LeaveOneOut split\n",
" loo = LeaveOneOut(n_splits=1)\n",
- "\n",
+ " \n",
" for trainset, testset in loo.split(ratings_dataset):\n",
" algo.fit(trainset) # Train the algorithm on the training set\n",
" anti_testset = trainset.build_anti_testset() # Build the anti test-set\n",
@@ -117,7 +115,7 @@
" anti_testset_top_n = top_n\n",
" return anti_testset_top_n\n",
"\n",
- "def precompute_information(movie_data):\n",
+ "def precomputed_information(movie_data):\n",
" \"\"\" Returns a dictionary that precomputes relevant information for evaluating in full mode\n",
" \n",
" Dictionary keys:\n",
@@ -139,8 +137,6 @@
" precomputed_dict[\"item_to_rank\"] = item_to_rank\n",
" \n",
" return precomputed_dict\n",
- " \n",
- "\n",
"\n",
"def create_evaluation_report(eval_config, sp_ratings, precomputed_dict, available_metrics):\n",
" \"\"\" Create a DataFrame evaluating various models on metrics specified in an evaluation config. \n",
@@ -160,7 +156,7 @@
" assert metric in available_metrics['split']\n",
" evaluation_function, parameters = available_metrics[\"split\"][metric]\n",
" evaluation_dict[model_name][metric] = evaluation_function(predictions, **parameters) \n",
- "\n",
+ " \n",
" # Type 2 : loo evaluations\n",
" if len(eval_config.loo_metrics) > 0:\n",
" print('Training loo predictions')\n",
@@ -197,7 +193,7 @@
},
{
"cell_type": "code",
- "execution_count": 184,
+ "execution_count": 60,
"id": "f1849e55",
"metadata": {},
"outputs": [],
@@ -219,7 +215,6 @@
"\n",
" return hit_rate\n",
"\n",
- "\n",
"def get_novelty(anti_testset_top_n, item_to_rank):\n",
" \"\"\"Compute the average novelty of the top-n recommendation over the users (full metric)\n",
" \n",
@@ -251,7 +246,7 @@
},
{
"cell_type": "code",
- "execution_count": 185,
+ "execution_count": 61,
"id": "704f4d2a",
"metadata": {},
"outputs": [
@@ -264,20 +259,99 @@
"- computing metric mae\n",
"- computing metric rmse\n",
"Training loo predictions\n",
- "Training full predictions\n"
+ "Training full predictions\n",
+ "Handling model baseline_2\n",
+ "Training split predictions\n",
+ "- computing metric mae\n",
+ "- computing metric rmse\n",
+ "Training loo predictions\n",
+ "Training full predictions\n",
+ "Handling model baseline_3\n",
+ "Training split predictions\n",
+ "- computing metric mae\n",
+ "- computing metric rmse\n",
+ "Training loo predictions\n",
+ "Training full predictions\n",
+ "Handling model baseline_4\n",
+ "Training split predictions\n",
+ "- computing metric mae\n",
+ "- computing metric rmse\n",
+ "Training loo predictions\n",
+ "Training full predictions\n",
+ "The data has been exported to the evaluation report\n"
]
},
{
- "ename": "AttributeError",
- "evalue": "'dict' object has no attribute 'to_csv'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[185], line 20\u001b[0m\n\u001b[1;32m 18\u001b[0m precomputed_dict \u001b[38;5;241m=\u001b[39m precompute_information(pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m../data/small/evidence/ratings.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m 19\u001b[0m evaluation_report \u001b[38;5;241m=\u001b[39m create_evaluation_report(EvalConfig, sp_ratings, precomputed_dict, AVAILABLE_METRICS)\n\u001b[0;32m---> 20\u001b[0m export_evaluation_report(evaluation_report)\n",
- "File \u001b[0;32m~/vscodeworkspace/recomsys/Analytics_UI/loaders.py:49\u001b[0m, in \u001b[0;36mexport_evaluation_report\u001b[0;34m(report)\u001b[0m\n\u001b[1;32m 47\u001b[0m report_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevaluation_report_\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpd\u001b[38;5;241m.\u001b[39mTimestamp\u001b[38;5;241m.\u001b[39mnow()\u001b[38;5;241m.\u001b[39mstrftime(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mY-\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mm-\u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 48\u001b[0m export_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m../data\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msmall\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mevaluations\u001b[39m\u001b[38;5;124m\"\u001b[39m, report_name)\n\u001b[0;32m---> 49\u001b[0m df_items\u001b[38;5;241m.\u001b[39mto_csv(export_path, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 50\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe data has been exported to the evaluation report\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m df_items\n",
- "\u001b[0;31mAttributeError\u001b[0m: 'dict' object has no attribute 'to_csv'"
- ]
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>mae</th>\n",
+ " <th>rmse</th>\n",
+ " <th>hit_rate</th>\n",
+ " <th>novelty</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>baseline_1</th>\n",
+ " <td>1.544940</td>\n",
+ " <td>1.776982</td>\n",
+ " <td>0.112150</td>\n",
+ " <td>99.405607</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>baseline_2</th>\n",
+ " <td>1.491063</td>\n",
+ " <td>1.844761</td>\n",
+ " <td>0.009346</td>\n",
+ " <td>429.942991</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>baseline_3</th>\n",
+ " <td>0.868139</td>\n",
+ " <td>1.066303</td>\n",
+ " <td>0.074766</td>\n",
+ " <td>99.405607</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>baseline_4</th>\n",
+ " <td>0.727803</td>\n",
+ " <td>0.927636</td>\n",
+ " <td>0.158879</td>\n",
+ " <td>57.328037</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " mae rmse hit_rate novelty\n",
+ "baseline_1 1.544940 1.776982 0.112150 99.405607\n",
+ "baseline_2 1.491063 1.844761 0.009346 429.942991\n",
+ "baseline_3 0.868139 1.066303 0.074766 99.405607\n",
+ "baseline_4 0.727803 0.927636 0.158879 57.328037"
+ ]
+ },
+ "execution_count": 61,
+ "metadata": {},
+ "output_type": "execute_result"
}
],
"source": [
@@ -298,7 +372,7 @@
"}\n",
"\n",
"sp_ratings = load_ratings(surprise_format=True)\n",
- "precomputed_dict = precompute_information(pd.read_csv(\"../data/small/evidence/ratings.csv\"))\n",
+ "precomputed_dict = precomputed_information(pd.read_csv(\"../data/tiny/evidence/ratings.csv\"))\n",
"evaluation_report = create_evaluation_report(EvalConfig, sp_ratings, precomputed_dict, AVAILABLE_METRICS)\n",
"export_evaluation_report(evaluation_report)"
]
@@ -320,7 +394,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.12.2"
+ "version": "3.11.8"
}
},
"nbformat": 4,
diff --git a/2_Evaluator_Block/loaders.py b/2_Evaluator_Block/loaders.py
index 7ccf4924644d425454af8e67a197425584dc22cc..a945f83808a759eef10202664fef0d239095dca1 100644
--- a/2_Evaluator_Block/loaders.py
+++ b/2_Evaluator_Block/loaders.py
@@ -24,7 +24,7 @@ def load_ratings(surprise_format=False):
return surprise_data
else:
return df_ratings
-
+print(load_ratings())
def load_items():
"""Loads items data.
@@ -44,12 +44,8 @@ def export_evaluation_report(report):
Returns:
DataFrame: Merged ratings and items data.
"""
- df_ratings = load_ratings()
- df_items = load_items()
- df_merge = pd.merge(df_ratings, df_items, on='movieId')
-
report_name = f"evaluation_report_{pd.Timestamp.now().strftime('%Y-%m-%d')}.csv"
- export_path = os.path.join("../data", "small", "evaluations", report_name)
- df_merge.to_csv(export_path, index=False)
+ export_path = os.path.join("../data", "tiny", "evaluations", report_name)
+ report.to_csv(export_path, index=False)
print("The data has been exported to the evaluation report")
- return df_merge
\ No newline at end of file
+ return report
\ No newline at end of file