File size: 4,030 Bytes
08db26d 02249fb 08db26d 02249fb 08db26d f6e244e 08db26d 38f046a 08db26d 38f046a 08db26d |
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 |
import gradio as gr
import pandas as pd
from sentiment_analyser import RandomAnalyser, RoBERTaAnalyser, ChatGPTAnalyser
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix
def plot_bar(value_counts):
fig, ax = plt.subplots(figsize=(6, 6))
value_counts.plot.barh(ax=ax)
ax.bar_label(ax.containers[0])
plt.title('Frequency of Predictions')
return fig
def plot_confusion_matrix(y_pred, y_true):
cm = confusion_matrix(y_true, y_pred, normalize='true')
fig, ax = plt.subplots(figsize=(6, 6))
labels = []
for label in SENTI_MAPPING.keys():
if (label in y_pred.values) or (label in y_true.values):
labels.append(label)
disp = ConfusionMatrixDisplay(confusion_matrix=cm,
display_labels=labels)
disp.plot(cmap="Blues", values_format=".2f", ax=ax, colorbar=False)
plt.title("Normalized Confusion Matrix")
return fig
def classify(num: int):
samples_df = df.sample(num)
X = samples_df['Text'].tolist()
y = samples_df['Label']
roberta = MODEL_MAPPING[OUR_MODEL]
y_pred = pd.Series(roberta.predict(X), index=samples_df.index)
samples_df['Predict'] = y_pred
bar = plot_bar(y_pred.value_counts())
cm = plot_confusion_matrix(y_pred, y)
plt.close()
return samples_df, bar, cm
def analysis(Text):
keys = []
values = []
for name, model in MODEL_MAPPING.items():
keys.append(name)
values.append(SENTI_MAPPING[model.predict([Text])[0]])
return pd.DataFrame([values], columns=keys)
MODEL_MAPPING = {
'Random': RandomAnalyser(),
'RoBERTa': RoBERTaAnalyser(),
'ChatGPT': RandomAnalyser(),
}
OUR_MODEL = 'RoBERTa'
SENTI_MAPPING = {
'negative': '😭',
'neutral': '😶',
'positive': '🥰'
}
TITLE = "Sentiment Analysis on Software Engineer Texts"
DESCRIPTION = (
"这里是第16组“睿王和他的五个小跟班”软工三迭代三模型演示页面。"
"模型链接：[Cloudy1225/stackoverflow-roberta-base-sentiment]"
"(https://huggingface.co/Cloudy1225/stackoverflow-roberta-base-sentiment) "
)
MAX_SAMPLES = 64
df = pd.read_csv('./SOF4423.csv')
with gr.Blocks(title=TITLE) as demo:
gr.HTML(f"<H1>{TITLE}</H1>")
gr.Markdown(DESCRIPTION)
gr.HTML("<H2>Model Inference</H2>")
gr.Markdown((
"在左侧文本框中输入文本并按回车键，右侧将输出情感分析结果。"
"这里我们展示了三种结果，分别是随机结果、模型结果和 ChatGPT 结果。"
))
with gr.Row():
with gr.Column():
text_input = gr.Textbox(label='Input',
placeholder="Enter a positive or negative sentence here...")
with gr.Column():
senti_output = gr.Dataframe(type="pandas", value=[['😋', '😋', '😋']],
headers=list(MODEL_MAPPING.keys()), interactive=False)
text_input.submit(analysis, inputs=text_input, outputs=senti_output, show_progress=True)
gr.HTML("<H2>Model Evaluation</H2>")
gr.Markdown((
"这里是在 StackOverflow4423 数据集上评估我们的模型。"
"滑动 Slider，将会从 StackOverflow4423 数据集中抽样出指定数量的样本，预测其情感标签。"
"并根据预测结果绘制标签分布图和混淆矩阵。"
))
input_models = list(MODEL_MAPPING)
input_n_samples = gr.Slider(
minimum=4,
maximum=MAX_SAMPLES,
value=8,
step=4,
label='Number of samples'
)
with gr.Row():
with gr.Column():
bar_plot = gr.Plot(label='Predictions Frequency')
with gr.Column():
cm_plot = gr.Plot(label='Confusion Matrix')
with gr.Row():
dataframe = gr.Dataframe(type="pandas", wrap=True, headers=['Text', 'Label', 'Predict'])
input_n_samples.change(fn=classify, inputs=input_n_samples, outputs=[dataframe, bar_plot, cm_plot])
demo.launch()
|