File size: 3,369 Bytes
2168cf5
faf61e8
 
 
2168cf5
 
6ce2f8e
2168cf5
7f68476
 
2168cf5
7f68476
ef26fd6
7f68476
 
a60235f
2168cf5
 
7f68476
 
 
 
 
 
2168cf5
42535f1
 
 
2168cf5
 
ef26fd6
7f68476
d961c51
faf61e8
7f68476
 
 
2168cf5
faf61e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c0d80b6
53c2635
92bbd4b
8289c6f
2168cf5
0fc2865
 
92bbd4b
0fc2865
8289c6f
c0d80b6
2168cf5
faf61e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from transformers import pipeline
import matplotlib.pyplot as plt
import twitter_scraper as ts


import gradio as gr
from gradio.mix import Parallel

pretrained_sentiment = "w11wo/indonesian-roberta-base-sentiment-classifier"
pretrained_ner = "cahya/bert-base-indonesian-NER"

sentiment_pipeline = pipeline(
    "sentiment-analysis",
    model=pretrained_sentiment,
    tokenizer=pretrained_sentiment,
    return_all_scores=True
)

ner_pipeline = pipeline(
    "ner",
    model=pretrained_ner,
    tokenizer=pretrained_ner
)

examples = [
    "Jokowi sangat kecewa dengan POLRI atas kerusuhan yang terjadi di Malang",
    "Lesti marah terhadap perlakuan KDRT yang dilakukan oleh Bilar",
    "Ungkapan rasa bahagia diutarakan oleh Coki Pardede karena kebabasannya dari penjara"
]

def sentiment_analysis(text):
    output = sentiment_pipeline(text)
    return {elm["label"]: elm["score"] for elm in output[0]}

def ner(text):
    output = ner_pipeline(text)
    return {"text": text, "entities": output}

def sentiment_df(df):
    text_list = list(df["Text"].astype(str).values)
    result = [sentiment_analysis(text) for text in text_list]
    df['Label'] = [pred['label'] for pred in result]
    df['Score'] = [round(pred['Score'], 3) for pred in result]
    return df


def twitter_analyzer(keyword, max_tweets):
    df = ts.scrape_tweets(keyword, max_tweets=max_tweets)
    df["Text"] = df["Text"].apply(ts.preprocess_text)
    df = sentiment_df(df)
    fig = plt.figure()
    df.groupby(["Label"])["Text"].count().plot.pie(autopct="%.1f%%", figsize=(6,6))
    return fig, df[["URL", "Text", "Label", "Score"]]

sentiment_demo = gr.Interface(
    fn=sentiment_analysis,
    inputs="text",
    outputs="label")

ner_demo = gr.Interface(
    ner,
    "text",
    gr.HighlightedText(),
    examples=examples)

if __name__ == "__main__":

    with gr.Blocks() as demo:

        gr.Markdown("""Entity Based Sentiment Analysis Indonesia""")

        gr.Markdown(
            """
            """
            )

        with gr.Tab("Single Input"):
            Parallel(
                    sentiment_demo, ner_demo,
                    inputs=gr.Textbox(lines=10, label="Input Text", placeholder="Enter sentences here..."),
                    examples=examples
                    )

        with gr.Tab("Twitter"):
            with gr.Blocks():
                with gr.Row():
                    with gr.Column():
                        keyword_textbox = gr.Textbox(lines=1, label="Keyword")
                        max_tweets_component = gr.Number(value=10, label="Total of Tweets to Scrape", precision=0)
                        button = gr.Button("Submit")

                    plot_component = gr.Plot(label="Pie Chart of Sentiments")
                dataframe_component = gr.DataFrame(type="pandas",
                                                label="Dataframe",
                                                max_rows=(20,'fixed'),
                                                overflow_row_behaviour='paginate',
                                                wrap=True)

        gr.Markdown(
                """

                """

            )

        button.click(twitter_analyzer,
                    inputs=[keyword_textbox, max_tweets_component],
                    outputs=[plot_component, dataframe_component])

    demo.launch(inbrowser=True)