File size: 5,651 Bytes
97a93cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
import spaces
import gradio as gr
import numpy as np
import pandas as pd
import time

css="""
#col-left {
    margin: 0 auto;
    max-width: 640px;
}
#col-right {
    margin: 0 auto;
    max-width: 640px;
}
.grid-container {
  display: flex;
  align-items: center;
  justify-content: center;
  gap:10px
}

.image {
  width: 128px; 
  height: 128px; 
  object-fit: cover; 
}

.text {
  font-size: 16px;
}
"""
emotion_columns = ['admiration', 'amusement', 'anger', 'annoyance', 'approval',
                   'caring', 'confusion', 'curiosity', 'desire', 'disappointment',
                   'disapproval', 'disgust', 'embarrassment', 'excitement', 'fear',
                   'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism',
                   'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise','neutral']

def load_text(text_path: str) -> str:
    with open(text_path, 'r', encoding='utf-8') as f:
        text = f.read()

    return text

def select_checkbox(name):
    if name =="All":
        return gr.CheckboxGroup(value=emotion_columns)
    elif name =="None":
        return []
    elif name =="Positive":
        return ["admiration","amusement","approval","caring","curiosity","desire","excitement","gratitude","joy","love","optimism","pride","relief"]
    elif name =="Negative":
        return ["anger","annoyance","disappointment","disapproval","disgust","fear","grief","embarrassment","remorse","sadness"]
    else:
        return ["confusion","nervousness","neutral","realization","surprise"]
def process_datas(checked_emotions,mode="filter",max_data=100,skip_data=0):
    checked_emotions = sorted(checked_emotions)
    
    df = pd.read_parquet("hf://datasets/google-research-datasets/go_emotions/raw/train-00000-of-00001.parquet")
    
     
    def filter_emotions(emotions):
        unchecked = emotion_columns.copy()
        condition_checked = np.all(df[emotions] == 1, axis=1)
        for emotion in checked_emotions:
            unchecked.remove(emotion)
        condition_unchecked = np.all(df[unchecked] == 0, axis=1)
        filtered_df = df[condition_checked & condition_unchecked]
        return filtered_df
    
    def df_to_text(df):
        df = df.iloc[skip_data:]
        if len(filtered_df) == 0:
            return ""
        texts=(df.head(max_data)[['text']].to_string(index=False,max_colwidth=None))
        trimmed_texts = [line.strip() for line in texts.split('\n')[1:] if line.strip()]
        return "\n".join(trimmed_texts)
    
    if mode == "filter":
        filtered_df = filter_emotions(checked_emotions)
        count = (len(filtered_df))
        trimmed_texts = df_to_text(filtered_df)
        
        last_count = min(count,(skip_data+max_data))
        label = f"{skip_data+1} - {last_count} of {count}"

        label_texts = [f"[{emotion}]" for emotion in checked_emotions]

        output_text = "+".join(label_texts)+"\n"+trimmed_texts
        output_label = label
    else:
        max_data = max(1,int(max_data/len(checked_emotions)))
        text_arrays = []
        for emotion in checked_emotions:
            text_arrays.append(f"[{emotion}]")
            filtered_df = filter_emotions([emotion])
            trimmed_texts = df_to_text(filtered_df)
            text_arrays.append(trimmed_texts)
            text_arrays.append("\n")
        print(text_arrays)
        output_text = "\n".join(text_arrays)
        output_label = f"{len(checked_emotions)} x {max_data}"
             

    return output_text,output_label,",".join(checked_emotions)


with gr.Blocks(css=css, elem_id="demo-container") as demo:
    with gr.Column():
        gr.HTML(load_text("demo_header.html"))
        gr.HTML(load_text("demo_tools.html"))
    with gr.Row():
        with gr.Column():
            with gr.Row(equal_height=True):
                mode_group = gr.Radio(choices=["filter","list"],label="Mode",value="filter")
                selection_name = gr.Dropdown(label="Select",choices=["All","None","Positive","Negative","Neutral"],value="All")
                selection_btn= gr.Button("Update Selection")
            checkbox_group = gr.CheckboxGroup(choices=emotion_columns,label="Emotions",value=["love"])
            btn= gr.Button("View Data",variant="primary")
            with gr.Row():
                max_data = gr.Slider(
                                label="Max Data",
                                minimum=0,
                                maximum=540,
                                step=10,
                                value=50,info="returning large data is heavy action,if you need more copy the space")
                skip_data = gr.Slider(
                                label="Skip Data",
                                minimum=0,
                                maximum=100000,
                                step=1,
                                value=0)
        with gr.Column():
            with gr.Row():
                data_size = gr.Textbox(label="Data Count",scale=1)
                checked_size = gr.Textbox(label="Checked",scale=2)

            text_out = gr.TextArea(label="Output", elem_id="output-text")
                    
    btn.click(fn=process_datas, inputs=[checkbox_group,mode_group,max_data,skip_data], outputs =[text_out,data_size,checked_size], api_name='infer')
    selection_btn.click(fn=select_checkbox,inputs=[selection_name],outputs=[checkbox_group])
    gr.Examples(
               examples=[
                    
                    ],
                inputs=[],
                
    )
    gr.HTML(
       gr.HTML(load_text("demo_footer.html"))
    )

    if __name__ == "__main__":
        demo.launch()