.

app.py

@@ -3,10 +3,11 @@ from cw2 import *
 
 data_tiny = pd.read_json('datasets/sample_tiny.json', lines=True)
 data_small = pd.read_json('datasets/sample_small.json', lines=True)
-# data_100k_lines = pd.read_json('datasets/sample_100k_lines.json', lines=True)
-# data_400k_lines = pd.read_json('datasets/sample_400k_lines.json', lines=True)
+data_100k_lines = pd.read_json('datasets/sample_100k_lines.json.gz', lines=True, compression='gzip')
+data_400k_lines = pd.read_json('datasets/sample_400k_lines.json.gz', lines=True, compression='gzip')
+data_600k_lines = pd.read_json('datasets/sample_600k_lines.json.gz', lines=True, compression='gzip')
 
-for dataset in [data_tiny, data_small]:#, data_100k_lines, data_400k_lines]:
+for dataset in [data_tiny, data_small, data_100k_lines, data_400k_lines, data_600k_lines]:
     dataset['visitor_continent'] = dataset['visitor_country'].apply(country_code_to_continent)
 
 
@@ -51,7 +52,7 @@ with gr.Blocks(css="""
         with gr.Column(scale=1, variant='panel', elem_id="space_between"):
             t2a_doc_uuid = gr.Textbox(value="140228101942-d4c9bd33cc299cc53d584ca1a4bf15d9", label="Enter document UUID:")
             selected_dataset = gr.Radio(label="Choose dataset size:",
-                                        choices=['tiny', 'small', '100k_lines', '400k_lines'],
+                                        choices=['tiny', 'small', '100k_lines', '400k_lines', '600k_lines'],
                                         interactive=True,
                                         value='small')
             req_1_submit = gr.Button(value="Generate graphs", elem_id="submit_button")
@@ -71,7 +72,7 @@ with gr.Blocks(css="""
         with gr.Row():
             with gr.Column(scale=1, variant='panel', elem_id="space_between"):
                 selected_dataset_3 = gr.Radio(label="Choose dataset size:",
-                                              choices=['tiny', 'small', '100k_lines', '400k_lines'],
+                                              choices=['tiny', 'small', '100k_lines', '400k_lines', '600k_lines'],
                                               interactive=True,
                                               value='small')
         with gr.Row():
@@ -90,7 +91,7 @@ with gr.Blocks(css="""
         with gr.Row():
             with gr.Column(scale=1, variant='panel', elem_id="space_between"):
                 selected_dataset_4 = gr.Radio(label="Choose dataset size:",
-                                              choices=['tiny', 'small', '100k_lines', '400k_lines'],
+                                              choices=['tiny', 'small', '100k_lines', '400k_lines', '600k_lines'],
                                               interactive=True,
                                               value='small')
         with gr.Row():
@@ -114,7 +115,7 @@ with gr.Blocks(css="""
     with gr.Row():
         with gr.Column(scale=1, variant='panel', elem_id="space_between"):
             selected_dataset_5 = gr.Radio(label="Choose dataset size:",
-                                          choices=['tiny', 'small', '100k_lines', '400k_lines'],
+                                          choices=['tiny', 'small', '100k_lines', '400k_lines', '600k_lines'],
                                           interactive=True,
                                           value='small')
             t5_doc_uuid = gr.Textbox(value="100713205147-2ee05a98f1794324952eea5ca678c026", label="Enter document UUID:")

datasets/sample_100k_lines.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4863c1c55572a940d0ce4bfb9edb89dfc9106028b58370d1f24d8afb8f48384
+size 3780560