formatting

Azure · May 9, 2023 · afa2be0 · afa2be0
1 parent d26188e
commit afa2be0
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 10 deletions.
diff --git a/cli/foundation-models/system/finetune/summarization/download-dataset.py b/cli/foundation-models/system/finetune/summarization/download-dataset.py
@@ -40,7 +40,9 @@
     )
 
 train_df = pd.read_json(os.path.join(args.download_dir, "train.jsonl"), lines=True)
-validation_df = pd.read_json(os.path.join(args.download_dir, "validation.jsonl"), lines=True)
+validation_df = pd.read_json(
+    os.path.join(args.download_dir, "validation.jsonl"), lines=True
+)
 # this dataset doesn't have test data, so split the validation_df into test_df and validation_df
 test_df = validation_df.sample(frac=0.5, random_state=42)
 validation_df.drop(test_df.index, inplace=True)
@@ -52,13 +54,15 @@
 
 # save 20% of the rows from the dataframes into files with small_ prefix in the ./news-summary-dataset folder
 train_df.sample(frac=0.2).to_json(
-    os.path.join(args.download_dir,"small_train.jsonl"), orient="records", lines=True
+    os.path.join(args.download_dir, "small_train.jsonl"), orient="records", lines=True
 )
 validation_df.sample(frac=0.2).to_json(
-    os.path.join(args.download_dir,"small_validation.jsonl"), orient="records", lines=True
+    os.path.join(args.download_dir, "small_validation.jsonl"),
+    orient="records",
+    lines=True,
 )
 test_df.sample(frac=0.2).to_json(
-    os.path.join(args.download_dir,"small_test.jsonl"), orient="records", lines=True
+    os.path.join(args.download_dir, "small_test.jsonl"), orient="records", lines=True
 )
 
 
@@ -68,7 +72,7 @@
 import json
 
 test_df = pd.read_json(
-    os.path.join(args.download_dir,"small_test.jsonl"), orient="records", lines=True
+    os.path.join(args.download_dir, "small_test.jsonl"), orient="records", lines=True
 )
 # take 1 random sample
 test_df = test_df.sample(n=1)
@@ -79,5 +83,5 @@
 # create a json object with the key as "inputs" and value as a list of values from the article column of the test dataframe
 test_json = {"inputs": {"input_string": test_df["article"].tolist()}}
 # save the json object to a file named sample_score.json in the ./emotion-dataset folder
-with open(os.path.join(args.download_dir,"sample_score.json"), "w") as f:
+with open(os.path.join(args.download_dir, "sample_score.json"), "w") as f:
     json.dump(test_json, f)
diff --git a/sdk/python/foundation-models/system/finetune/summarization/news-summary.ipynb b/sdk/python/foundation-models/system/finetune/summarization/news-summary.ipynb
@@ -85,9 +85,9 @@
     "except:\n",
     "    workspace_ml_client = MLClient(\n",
     "        credential,\n",
-    "        subscription_id = \"<SUBSCRIPTION_ID>\",\n",
-    "        resource_group_name =  \"<RESOURCE_GROUP>\",\n",
-    "        workspace_name =  \"WORKSPACE_NAME>\",\n",
+    "        subscription_id=\"<SUBSCRIPTION_ID>\",\n",
+    "        resource_group_name=\"<RESOURCE_GROUP>\",\n",
+    "        workspace_name=\"WORKSPACE_NAME>\",\n",
     "    )\n",
     "\n",
     "# the models, fine tuning pipelines and environments are available in the AzureML system registry, \"azureml-preview\"\n",
@@ -188,7 +188,8 @@
    "source": [
     "# download the dataset using the helper script. This needs datasets library: https://pypi.org/project/datasets/\n",
     "import os\n",
-    "exit_status=os.system(\"python ./download-dataset.py\")\n",
+    "\n",
+    "exit_status = os.system(\"python ./download-dataset.py\")\n",
     "if exit_status != 0:\n",
     "    raise Exception(\"Error downloading dataset\")"
    ]