Add time series sales data as an example dataset

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/online_retail_data.csv filter=lfs diff=lfs merge=lfs -text

data_sources/upload_file.py

@@ -1,8 +1,16 @@
 import pandas as pd
 import sqlite3
+import csv
+
+def get_delimiter(file_path, bytes = 4096):
+    sniffer = csv.Sniffer()
+    data = open(file_path, "r").read(bytes)
+    delimiter = sniffer.sniff(data).delimiter
+    return delimiter
 
 def process_data_upload(data_file, session_hash):
-    df = pd.read_csv(data_file, sep=";")
+    delimiter = get_delimiter(data_file)
+    df = pd.read_csv(data_file, sep=delimiter)
 
     # Read each sheet and store data in a DataFrame
     #data = df.parse(sheet_name)
@@ -10,6 +18,10 @@ def process_data_upload(data_file, session_hash):
     # ...
     df.columns = df.columns.str.replace(' ', '_')
     df.columns = df.columns.str.replace('/', '_')
+
+    for column in df.columns:
+        if "date" in column.lower() or "time" in column.lower():
+            df[column] = pd.to_datetime(df[column])
     
     connection = sqlite3.connect(f'data_source_{session_hash}.db')
     print("Opened database successfully");

functions/chat_functions.py

@@ -67,18 +67,23 @@ def example_display(input):
         display = True
     else:
         display = False
-    return gr.update(visible=display)
+    return [gr.update(visible=display),gr.update(visible=display)]
 
 css= ".file_marker .large{min-height:50px !important;} .example_btn{max-width:300px;}"
 
 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>")
-    example_file = gr.File(visible=False, value="samples/bank_marketing_campaign.csv")
-    example_btn = gr.Button(value="Try Me: bank_marketing_campaign.csv", elem_classes="example_btn", size="md", variant="primary")
+    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'])
-    example_btn.click(fn=run_example, inputs=example_file, outputs=file_output)
-    file_output.change(fn=example_display, inputs=file_output, outputs=example_btn)
+    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])
 
     @gr.render(inputs=file_output)
     def data_options(filename, request: gr.Request):

samples/online_retail_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d4e4f72b6bc62ce831e8243bc02e491fda0085c1d94f3075063411539b1f04
+size 45580673