Update app.py

app.py

@@ -23,9 +23,29 @@ import json
 import numpy as np
 import gradio as gr
 
+HF_TOKEN = os.environ.get("HF_TOKEN")
 CHOICES = ["SNOMED", "LOINC", "CQM"]
 JSONOBJ = """{"items":{"item":[{"id": "0001","type": null,"is_good": false,"ppu": 0.55,"batters":{"batter":[{ "id": "1001", "type": "Regular" },{ "id": "1002", "type": "Chocolate" },{ "id": "1003", "type": "Blueberry" },{ "id": "1004", "type": "Devil's Food" }]},"topping":[{ "id": "5001", "type": "None" },{ "id": "5002", "type": "Glazed" },{ "id": "5005", "type": "Sugar" },{ "id": "5007", "type": "Powdered Sugar" },{ "id": "5006", "type": "Chocolate with Sprinkles" },{ "id": "5003", "type": "Chocolate" },{ "id": "5004", "type": "Maple" }]}]}}"""
 
+
+def profile_dataset(dataset=datasetSNOMED, username="awacke1", token=HF_TOKEN, dataset_name="awacke1/SNOMED-CT-Code-Value-Semantic-Set.csv"):
+    df = pd.read_csv(dataset.name)
+    if len(df.columns) <= 15:
+        profile = pp.ProfileReport(df, title=f"{dataset_name} Report")
+    else:
+        profile = pp.ProfileReport(df, title=f"{dataset_name} Report", minimal = True)
+    
+    repo_url = create_repo(f"{username}/{dataset_name}", repo_type = "space", token = token, space_sdk = "static", private=False)
+    
+    profile.to_file("./index.html")
+
+    upload_file(path_or_fileobj ="./index.html", path_in_repo = "index.html", repo_id =f"{username}/{dataset_name}", repo_type = "space", token=token)
+    readme = f"---\ntitle: {dataset_name}\nemoji: ✨\ncolorFrom: green\ncolorTo: red\nsdk: static\npinned: false\ntags:\n- dataset-report\n---"    
+    with open("README.md", "w+") as f:
+        f.write(readme)
+    upload_file(path_or_fileobj ="./README.md", path_in_repo = "README.md", repo_id =f"{username}/{dataset_name}", repo_type = "space", token=token)
+    return f"Your dataset report will be ready at {repo_url}"
+
 #def lowercase_title(example):
 #    return {"Description": example[title].lower()}
 
@@ -36,13 +56,16 @@ JSONOBJ = """{"items":{"item":[{"id": "0001","type": null,"is_good": false,"ppu"
 #def fn(    text1,    text2,    num,    slider1,    slider2,    single_checkbox,    checkboxes,    radio,    dropdown,    im1,    im2,    im3,    im4,
 #    video,    audio1,    audio2,    file,    df1,    df2,):
 def fn(    text1,    text2,    single_checkbox,    checkboxes,    radio,    im4,  file,    df1,    df2,):
+
     searchTerm = text1
     searchTermSentence = text2
-    #my_dataset_dictionary['train'][0]
+    
     start_with_searchTermLOINC = datasetLOINC.filter(lambda example: example["Description"].startswith('Allergy'))    #Allergy
     start_with_searchTermSNOMED = datasetSNOMED.filter(lambda example: example["Description"].startswith('Hospital'))    #Hospital
     start_with_searchTermCQM = dataseteCQM.filter(lambda example: example["Description"].startswith('Telephone'))    #Telephone
     
+    returnMsg=profile_dataset()
+    print(returnMsg)
     try:
         top1matchLOINC = json.loads(start_with_searchTermLOINC['train'][0])
         top1matchSNOMED = json.loads(start_with_searchTermSNOMED['train'][0])
@@ -51,7 +74,8 @@ def fn(    text1,    text2,    single_checkbox,    checkboxes,    radio,    im4,
         print(start_with_searchTermLOINC)
         print(start_with_searchTermSNOMED )
         print(start_with_searchTermCQM )
-    
+    print(returnMsg)
+    print("Datasets Processed")
     
     return (
         #(text1 if single_checkbox else text2)        + ", selected:"        + ", ".join(checkboxes),  # Text