feature:chart visualization

app.py

@@ -4,9 +4,10 @@ import torch
 from collections import Counter
 from scipy.special import softmax
 import plotly.express as px
+import plotly.io as pio  # Add this import
 
 # Article string
-article_string = "Author: <a href=\"https://huggingface.co/FpOliveira\">Felipe Ramos de Oliveira</a>. Read more about our <a href=\"https://github.com/Silly-Machine/TuPi-Portuguese-Hate-Speech-Dataset\">The Portuguese hate speech dataset (TuPI) </a>."
+article_string = "Authors: <a href=\"https://huggingface.co/FpOliveira\">Felipe Oliveira</a> & <a href=\"https://huggingface.co/victoriadreis\">Victoria Reis</a>. Read more about our <a href=\"https://github.com/Silly-Machine/TuPi-Portuguese-Hate-Speech-Dataset\">The Portuguese hate speech dataset (TuPI) </a>."
 
 # App title
 app_title = "Portuguese hate speech identifier (Multiclass) - Identificador de discurso de ódio em português (Multiclasse)"
@@ -97,8 +98,6 @@ def most_frequent(array):
     occurence_count = Counter(array)
     return occurence_count.most_common(1)[0][0]
 
-
-# Prediction function
 def predict(s1, chosen_model):
     # Clear previous figure instance
     fig = None
@@ -133,21 +132,23 @@ def predict(s1, chosen_model):
     # Get the categories and probabilities for all classes
     all_categories = [hate_speech_categories[index] for index in valid_indices]
     all_probabilities = [logits[index] for index in valid_indices]
-    
-    # Create a bar plot using Plotly
+
     fig = px.bar(x=all_categories, y=all_probabilities, labels={'x': 'Categories', 'y': 'Probabilities'},
-                 title="Classes Predicted Probabilities", text=all_probabilities)
-    fig.update_traces(texttemplate='%{text:.4f}', textposition='outside')
-    fig.show()
-    
-    # # Save the figure as HTML
-    # html_figure = fig.to_html()
-    
-    # Get the categories and probabilities for the top two
-    top_category = [hate_speech_categories[index] for index in top_indices]
-    top_probability = [logits[index] for index in top_indices]
-    result = top_category[0], 1-top_probability[1]
-    return result
+             title="   ", 
+             text=all_probabilities, color_discrete_sequence=['#ff7400'])
+
+    fig.update_traces(texttemplate='%{text:.2f}', textposition='outside')
+
+    # Rotate the text in x-axis by 90 degrees
+    fig.update_layout(xaxis_tickangle=-90)
+
+    # Increase the space around the chart
+    fig.update_layout(margin=dict(l=50, r=50, b=100, t=100))
+
+    # Set the y-axis range to go up to 1.1
+    fig.update_layout(yaxis=dict(range=[0, 1.1]))
+
+    return fig
 
 # Input components
 inputs = [
@@ -155,14 +156,14 @@ inputs = [
     gr.Dropdown(label="Model", choices=user_friendly_name_list, value=user_friendly_name_list[0])
 ]
 
-# Output components
 outputs = [
-    gr.Label(label="Predominant category"),
-    gr.Label(label="Probability"),
+    gr.Plot(label="Classes Predicted Probabilities")  # Add this line
 ]
 
-# Gradio interface
-gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title=app_title,
-             description=app_description,
-             examples=app_examples,
-             article=article_string).launch()
+# Gradio interface without launching
+interface = gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title=app_title,
+                         description=app_description, examples=app_examples, article=article_string, live=False)
+
+# Launch the interface
+interface.launch()
+

flagged/log.csv

@@ -0,0 +1,2 @@
+Text,Model,Predominant category,Probability,flag,username,timestamp
+mds mas o viado vir responder meus status falando q a taylor foi racista foi o auge 😂😂,BERTimbau large (TuPi),"{""label"":null,""confidences"":null}","{""label"":null,""confidences"":null}",,,2023-12-04 14:13:25.289476