|
import csv |
|
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) |
|
|
|
|
|
def analyse_file(file): |
|
output_name = 'output.csv' |
|
with open(output_name, mode='w', newline='') as output: |
|
writer = csv.writer(output) |
|
header = ['Text', 'Label'] |
|
writer.writerow(header) |
|
model = MODEL_MAPPING[OUR_MODEL] |
|
with open(file.name) as f: |
|
for line in f: |
|
text = line[:-1] |
|
sentiment = model.predict([text]) |
|
writer.writerow([text, sentiment[0]]) |
|
return output_name |
|
|
|
|
|
MODEL_MAPPING = { |
|
'Random': RandomAnalyser(), |
|
'RoBERTa': RoBERTaAnalyser(), |
|
'ChatGPT': RandomAnalyser(), |
|
} |
|
|
|
OUR_MODEL = 'RoBERTa' |
|
|
|
SENTI_MAPPING = { |
|
'negative': '😭', |
|
'neutral': '😶', |
|
'positive': '🥰' |
|
} |
|
|
|
TITLE = "Sentiment Analysis on Software Engineer Texts" |
|
|
|
DESCRIPTION = { |
|
'en': ( |
|
"This is the demo page for our model: " |
|
"[Cloudy1225/stackoverflow-roberta-base-sentiment]" |
|
"(https://huggingface.co/Cloudy1225/stackoverflow-roberta-base-sentiment)." |
|
), |
|
'zh': ( |
|
"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)." |
|
) |
|
} |
|
|
|
PROMPT1 = { |
|
'en': ( |
|
"Enter text in the left text box and press Enter, and the sentiment analysis results will be output on the right. " |
|
"Here, we present three types of results, which come from random, our model, and ChatGPT." |
|
), |
|
'zh': ( |
|
"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。" |
|
) |
|
} |
|
|
|
PROMPT2 = { |
|
'en': ( |
|
"Upload a txt/csv file in the left file box, and the model will perform sentiment analysis on each line of the input text. " |
|
"You can download the output file on the right. " |
|
"The output file will be in CSV format with two columns: the original text, and the classification results." |
|
), |
|
'zh': ( |
|
"在左侧文件框中上传 txt/csv 文件,模型会对输入文本的每一行当作一个文本进行情感分析。" |
|
"可以在右侧下载输出文件,输出文件为两列 csv 格式,第一列为原始文本,第二列为分类结果。" |
|
) |
|
} |
|
|
|
PROMPT3 = { |
|
'en': ( |
|
"Here we evaluate our model on the StackOverflow4423 dataset. " |
|
"Sliding the slider will sample a specified number of samples from the StackOverflow4423 dataset and predict their sentiment labels. " |
|
"Based on the prediction results, a label distribution chart and a confusion matrix will be plotted." |
|
), |
|
'zh': ( |
|
"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。" |
|
) |
|
} |
|
|
|
DEFAULT_LANG = 'en' |
|
|
|
MAX_SAMPLES = 64 |
|
|
|
df = pd.read_csv('./SOF4423.csv') |
|
|
|
|
|
def set_language(lang): |
|
return DESCRIPTION[lang], PROMPT1[lang], PROMPT2[lang], PROMPT3[lang] |
|
|
|
|
|
with gr.Blocks(title=TITLE) as demo: |
|
with gr.Row(): |
|
with gr.Column(): |
|
gr.HTML(f"<H1>{TITLE}</H1>") |
|
with gr.Column(min_width=160): |
|
language_selector = gr.Radio( |
|
['en', 'zh'], label="Select Language", value=DEFAULT_LANG, |
|
interactive=True, show_label=False, container=False |
|
) |
|
|
|
description = gr.Markdown(DESCRIPTION[DEFAULT_LANG]) |
|
gr.HTML("<H2>Model Inference</H2>") |
|
prompt1 = gr.Markdown(PROMPT1[DEFAULT_LANG]) |
|
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='full') |
|
|
|
prompt2 = gr.Markdown(PROMPT2[DEFAULT_LANG]) |
|
with gr.Row(): |
|
with gr.Column(): |
|
file_input = gr.File(label='File', |
|
file_types=['.txt', '.csv']) |
|
with gr.Column(): |
|
file_output = gr.File(label='Output') |
|
file_input.upload(analyse_file, inputs=file_input, outputs=file_output) |
|
|
|
gr.HTML("<H2>Model Evaluation</H2>") |
|
prompt3 = gr.Markdown(PROMPT3[DEFAULT_LANG]) |
|
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]) |
|
|
|
language_selector.change(fn=set_language, inputs=language_selector, |
|
outputs=[description, prompt1, prompt2, prompt3]) |
|
|
|
demo.launch() |
|
|