Saving datasets for easier manipulation

epfl-ada · Dec 11, 2024 · 9cd0291 · 9cd0291
1 parent a229847
commit 9cd0291
Show file tree

Hide file tree

Showing 9 changed files with 3,061,571 additions and 1,744 deletions.
diff --git a/Pauline.ipynb b/Pauline.ipynb
@@ -1487,7 +1487,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "id": "082dcc01",
    "metadata": {},
    "outputs": [
@@ -1882,9 +1882,6 @@
     "\n",
     "    print(f\"There are {char_rating.shape[0]} rows in the merged dataset\")\n",
     "    return char_rating\n",
-    "\n",
-    "expanded_df = merge_imdb_and_dataset(imdb_votes, mov_char_data, \"data/raw/imdb\")\n",
-    "expanded_df.head(10)\n",
     "\n"
    ]
   },

diff --git a/data/clean/expanded/expanded_df.csv b/data/clean/expanded/expanded_df.csv
diff --git a/data/clean/expanded/merged_imdb_mov_char.csv b/data/clean/expanded/merged_imdb_mov_char.csv