Update download comments

SentimentClassification.ipynb

@@ -55,9 +55,12 @@
    ],
    "source": [
     "# Download the datasets\n",
+    "# The dataset can be downloaded through the `download_data.sh` script, which requires to set up\n",
+    "# Kaggle's CLI, or manually at https://www.kaggle.com/datasets/crowdflower/twitter-airline-sentiment\n",
     "if not os.path.isfile(\"local_datasets/twitter-airline-sentiment/Tweets.csv\"):\n",
     "    raise ValueError(\"Please launch the `download_data.sh` script to get datasets\")\n",
     "\n",
+    "\n",
     "train = pd.read_csv(\"local_datasets/twitter-airline-sentiment/Tweets.csv\", index_col=0)\n",
     "text_X = train[\"text\"]\n",
     "y = train[\"airline_sentiment\"]\n",
@@ -981,6 +984,15 @@
  "metadata": {
   "execution": {
    "timeout": 10800
+  },
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,

download_data.sh

@@ -2,8 +2,10 @@
 
 set -e
 
-# You need to have a valid ~/.kaggle/kaggle.json, that you can generate from "Create new API token"
-# on your account page in kaggle.com
+# You need to install kaggle using pip and then have a valid ~/.kaggle/kaggle.json, that you can 
+# generate from "Create new API token" on your account page in kaggle.com
+# Alternatively, the dataset can be downloaded manually at 
+# https://www.kaggle.com/datasets/crowdflower/twitter-airline-sentiment
 rm -rf local_datasets
 mkdir local_datasets
 cd local_datasets