gaspersic/openai-cookbook
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

updates embedding examples with new embedding model

Browse Source
This commit is contained in:
Logan Kilpatrick
2022-12-13 17:28:39 -06:00
committed by Ted Sanders
parent 7de3d50816
commit fd181ec78f
12 changed files with 12387 additions and 12390 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/Regression_using_embeddings.ipynb
View File

@ -20,7 +20,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Babbage similarity embedding performance on 1k Amazon reviews: mse=0.39, mae=0.38\n"
"Ada similarity embedding performance on 1k Amazon reviews: mse=0.60, mae=0.51\n"
]
}
],
@ -32,11 +32,13 @@
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
"\n",
"datafile_path = \"https://cdn.openai.com/API/examples/data/fine_food_reviews_with_embeddings_1k.csv\" # for your convenience, we precomputed the embeddings\n",
"df = pd.read_csv(datafile_path)\n",
"df[\"babbage_similarity\"] = df.babbage_similarity.apply(eval).apply(np.array)\n",
"# If you have not run the \"Obtain_dataset.ipynb\" notebook, you can download the datafile from here: https://cdn.openai.com/API/examples/data/fine_food_reviews_with_embeddings_1k.csv\n",
"datafile_path = \"./data/fine_food_reviews_with_embeddings_1k.csv\"\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(list(df.babbage_similarity.values), df.Score, test_size=0.2, random_state=42)\n",
"df = pd.read_csv(datafile_path)\n",
"df[\"ada_similarity\"] = df.ada_similarity.apply(eval).apply(np.array)\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(list(df.ada_similarity.values), df.Score, test_size=0.2, random_state=42)\n",
"\n",
"rfr = RandomForestRegressor(n_estimators=100)\n",
"rfr.fit(X_train, y_train)\n",
@ -45,7 +47,7 @@
"mse = mean_squared_error(y_test, preds)\n",
"mae = mean_absolute_error(y_test, preds)\n",
"\n",
"print(f\"Babbage similarity embedding performance on 1k Amazon reviews: mse={mse:.2f}, mae={mae:.2f}\")\n"
"print(f\"Ada similarity embedding performance on 1k Amazon reviews: mse={mse:.2f}, mae={mae:.2f}\")\n"
]
},
{
@ -57,7 +59,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Dummy mean prediction performance on Amazon reviews: mse=1.81, mae=1.08\n"
"Dummy mean prediction performance on Amazon reviews: mse=1.73, mae=1.03\n"
]
}
],
@ -70,10 +72,11 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"We can see that the embeddings are able to predict the scores with an average error of 0.39 per score prediction. This is roughly equivalent to predicting 2 out of 3 reviews perfectly, and 1 out of three reviews by a one star error."
"We can see that the embeddings are able to predict the scores with an average error of 0.60 per score prediction. This is roughly equivalent to predicting 1 out of 3 reviews perfectly, and 1 out of two reviews by a one star error."
]
},
{
@ -86,9 +89,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.9 ('openai')",
"display_name": "openai-cookbook",
"language": "python",
"name": "python3"
"name": "openai-cookbook"
},
"language_info": {
"codemirror_mode": {
@ -100,7 +103,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.9"
"version": "3.9.6"
},
"orig_nbformat": 4,
"vscode": {