Upload 2 files

data_sources/upload_file.py

@@ -8,9 +8,21 @@ def get_delimiter(file_path, bytes = 4096):
     delimiter = sniffer.sniff(data).delimiter
     return delimiter
 
+def read_file(file):
+    if file.endswith(('.csv', '.tsv', '.txt')) :
+        df = pd.read_csv(file, sep=get_delimiter(file))
+    elif file.endswith('.json'):
+        df = pd.read_json(file)
+    elif file.endswith('.xml'):
+        df = pd.read_xml(file)
+    elif file.endswith(('.xls','xlsx')):
+        df = pd.read_excel(file)
+    else:
+        raise ValueError(f'Unsupported filetype: {file}')
+    return df
+
 def process_data_upload(data_file, session_hash):
-    delimiter = get_delimiter(data_file)
-    df = pd.read_csv(data_file, sep=delimiter)
+    df = read_file(data_file)
 
     # Read each sheet and store data in a DataFrame
     #data = df.parse(sheet_name)

functions/chat_functions.py

@@ -73,14 +73,14 @@ css= ".file_marker .large{min-height:50px !important;} .example_btn{max-width:30
 
 with gr.Blocks(css=css) as demo:
     title = gr.HTML("<h1 style='text-align:center;'>Virtual Data Analyst</h1>")
-    description = gr.HTML("<p style='text-align:center;'>Upload a CSV file and chat with our virtual data analyst to get insights on your data set</p>")
+    description = gr.HTML("<p style='text-align:center;'>Upload a data file and chat with our virtual data analyst to get insights on your data set. Currently accepts CSV, TSV, TXT, XLS, XLSX, XML, and JSON files. Try a sample file to get started!</p>")
     example_file_1 = gr.File(visible=False, value="samples/bank_marketing_campaign.csv")
     example_file_2 = gr.File(visible=False, value="samples/online_retail_data.csv")
     with gr.Row():
         example_btn_1 = gr.Button(value="Try Me: bank_marketing_campaign.csv", elem_classes="example_btn", size="md", variant="primary")
         example_btn_2 = gr.Button(value="Try Me: online_retail_data.csv", elem_classes="example_btn", size="md", variant="primary")
 
-    file_output = gr.File(label="CSV File", show_label=True, elem_classes="file_marker", file_types=['.csv'])
+    file_output = gr.File(label="Data File (CSV, TSV, TXT, XLS, XLSX, XML, JSON)", show_label=True, elem_classes="file_marker", file_types=['.csv','.xlsx','.txt','.json','.xml','.xls','.tsv'])
     example_btn_1.click(fn=run_example, inputs=example_file_1, outputs=file_output)
     example_btn_2.click(fn=run_example, inputs=example_file_2, outputs=file_output)
     file_output.change(fn=example_display, inputs=file_output, outputs=[example_btn_1, example_btn_2])