Real life ezample test completed, script is working

wiktorflorian · May 31, 2023 · b1cc560 · b1cc560
1 parent 1a8ab0f
commit b1cc560
Showing 1 changed file with 61 additions and 2 deletions.
diff --git a/csv_divider/csv_divider.ipynb b/csv_divider/csv_divider.ipynb
@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -132,7 +132,7 @@
     "max_file_size_mb = 75\n",
     "\n",
     "\n",
-    "split_csv(input_path, output_dir, max_file_size_mb, delimiter=',')"
+    "split_csv(input_path, output_dir, max_file_size_mb, delimiter=',', output_file_name='chunk')"
    ]
   },
   {
@@ -420,6 +420,65 @@
     "# Concatenated data head\n",
     "concatenated_data.head()"
    ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Real life example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "~/python_sc/Learning/Python_learning/NLTK/data/amazon.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Get the current working directory\n",
+    "current_dir = os.getcwd()\n",
+    "\n",
+    "input_path = \"~/python_sc/Learning/Python_learning/NLTK/data/amazon.csv\"\n",
+    "\n",
+    "\n",
+    "# Path to the amazon.csv file\n",
+    "file_path = os.path.join(input_path, \"amazon.csv\")\n",
+    "print(file_path)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved 1 / 2\n",
+      "Saved 2 / 2\n"
+     ]
+    }
+   ],
+   "source": [
+    "# specifyings args and kwargs, file_path, output_dir, max file size in delimiter bytes, and delimier\n",
+    "input_path = \"/Users/florian/python_sc/Learning/Python_learning/NLTK/data/amazon.csv\"\n",
+    "output_dir = \"/Users/florian/python_sc/Learning/Python_learning/NLTK/data\"\n",
+    "max_file_size_mb = 75\n",
+    "\n",
+    "\n",
+    "split_csv(input_path, output_dir, max_file_size_mb, delimiter=',', output_file_name=\"amazon\")"
+   ]
   }
  ],
  "metadata": {