import streamlit as st
from sentiment_model import PretrainedSentimentAnalyzer
import pandas as pd
import matplotlib.pyplot as plt
import plotly.graph_objects as go
import pandas as pd
import re
# Create an instance of the PretrainedSentimentAnalyzer class
analyzer = PretrainedSentimentAnalyzer(None, None, None, None)
# Define the Streamlit app
def main():
st.title("Early Depression Detection System")
# Get user input
option = st.selectbox("Select an option:", ("Enter a sentence", "Upload a CSV file"))
if option == "Enter a sentence":
text = st.text_input("Enter a sentence:")
# Perform sentiment analysis
if st.button("Analyze"):
if not text or len(text) == 1:
st.write("Enter valid text")
else:
sentiment = analyzer.predict([text], inverse_transform=True)[0]
st.write("Sentiment Analysis Results:")
st.write("Sentiment:", sentiment['label'])
#st.write("Score:", sentiment['score'])
if sentiment['label'] == 'negative':
st.write(scan(text))
st.write("Please call the helpline number:")
st.write("Beyond Blue: 1300 659 467")
st.write("Mental Health Emergency: 13 14 65")
else:
st.write("No Depression Detected")
elif option == "Upload a CSV file":
file = st.file_uploader("Upload a CSV file:")
if file is not None:
# Check file format
if file.name.endswith('.csv'):
# Perform sentiment analysis on the uploaded file
df = pd.read_csv(file)
if st.button("Analyze"):
# with st.spinner("Predicting..."):
# column = df.columns[1]
# data = df[column].astype(str).tolist()
# sentiments = analyzer.predict(data, inverse_transform=True)
# df['sentiment'] = [s['label'] for s in sentiments]
spinner_placeholder = st.markdown("""
""", unsafe_allow_html=True)
column = df.columns[1]
data = df[column].astype(str).tolist()
sentiments = analyzer.predict(data, inverse_transform=True)
df['Prediction'] = [s['label'] for s in sentiments]
# Clear the spinner
spinner_placeholder.empty()
st.write("Sentiment Analysis Results:")
st.write(df)
sentiment_counts = df['Prediction'].value_counts()
sentiment_dict = {'Positive': 0, 'Neutral': 0, 'Negative': 0}
for sentiment in sentiment_counts.index:
if sentiment == 'positive':
sentiment_dict['Positive'] += sentiment_counts[sentiment]
elif sentiment == 'neutral':
sentiment_dict['Neutral'] += sentiment_counts[sentiment]
elif sentiment == 'negative':
sentiment_dict['Negative'] += sentiment_counts[sentiment]
st.write("Sentiment Counts:")
for sentiment, count in sentiment_dict.items():
st.write(sentiment + ":", count)
labels = list(sentiment_dict.keys())
sizes = list(sentiment_dict.values())
colors = ['green', 'white', 'red'] # colors for Positive, Neutral, Negative
fig = go.Figure(data=[go.Pie(labels=labels, values=sizes,hole=.2, marker=dict(colors=colors))])
fig.update_layout(
title="Sentiment Analysis",
showlegend=True,
legend_title="Sentiment",
uniformtext_minsize=12,
uniformtext_mode='hide'
)
st.plotly_chart(fig)
negative_data = df[df['Prediction'] == 'negative']
# Create a df that only has the tweets column
tweets_data = negative_data['Tweets']
st.write("Depressed Tweets")
st.write(scan(tweets_data))
st.write("Please call the helpline number:")
st.write("Beyond Blue: 1300 659 467")
st.write("Mental Health Emergency: 13 14 65")
else:
st.write("File type not supported")
def scan(tweets_data):
contractions_dict = { "ain't": "are not","'s":" is","aren't": "are not",
"can't": "cannot","can't've": "cannot have",
"'cause": "because","could've": "could have","couldn't": "could not",
"couldn't've": "could not have", "didn't": "did not","doesn't": "does not",
"don't": "do not","hadn't": "had not","hadn't've": "had not have",
"hasn't": "has not","haven't": "have not","he'd": "he would",
"he'd've": "he would have","he'll": "he will", "he'll've": "he will have",
"how'd": "how did","how'd'y": "how do you","how'll": "how will",
"I'd": "I would", "I'd've": "I would have","I'll": "I will",
"I'll've": "I will have","I'm": "I am","I've": "I have", "isn't": "is not",
"it'd": "it would","it'd've": "it would have","it'll": "it will",
"it'll've": "it will have", "let's": "let us","ma'am": "madam",
"mayn't": "may not","might've": "might have","mightn't": "might not",
"mightn't've": "might not have","must've": "must have","mustn't": "must not",
"mustn't've": "must not have", "needn't": "need not",
"needn't've": "need not have","o'clock": "of the clock","oughtn't": "ought not",
"oughtn't've": "ought not have","shan't": "shall not","sha'n't": "shall not",
"shan't've": "shall not have","she'd": "she would","she'd've": "she would have",
"she'll": "she will", "she'll've": "she will have","should've": "should have",
"shouldn't": "should not", "shouldn't've": "should not have","so've": "so have",
"that'd": "that would","that'd've": "that would have", "there'd": "there would",
"there'd've": "there would have", "they'd": "they would",
"they'd've": "they would have","they'll": "they will",
"they'll've": "they will have", "they're": "they are","they've": "they have",
"to've": "to have","wasn't": "was not","we'd": "we would",
"we'd've": "we would have","we'll": "we will","we'll've": "we will have",
"we're": "we are","we've": "we have", "weren't": "were not","what'll": "what will",
"what'll've": "what will have","what're": "what are", "what've": "what have",
"when've": "when have","where'd": "where did", "where've": "where have",
"who'll": "who will","who'll've": "who will have","who've": "who have",
"why've": "why have","will've": "will have","won't": "will not",
"won't've": "will not have", "would've": "would have","wouldn't": "would not",
"wouldn't've": "would not have","y'all": "you all", "y'all'd": "you all would",
"y'all'd've": "you all would have","y'all're": "you all are",
"y'all've": "you all have","you'd": "you would","you'd've": "you would have",
"you'll": "you will","you'll've": "you will have", "you're": "you are",
"you've": "you have"}
absolute_words = ["I", "feeling", "feels", "always", "never", "completely", "totally",
"absolutely", "must", "should", "all", "every", "none", "nothing",
"everyone", "everything", "only", "impossible", "forever", "can’t",
"cannot", "won’t", "will not", "no one", "no-one", "every time",
"low", "everytime", "difficult", "difficulty", "nightmare", "bored",
"disaster", "irritate", "broken", "hurt", "lost", "book", "alone",
"journal", "tool", "fight", "highway", "stupid", "disgusted", "stress",
"hostile", "reserved", "danger", "funeral", "respect", "news", "toothache",
"vomit", "sick", "beach", "office", "window", "phase", "plant", "hotel",
"friend", "teacher", "betray", "poster", "grief", "puppy", "safe", "kiss",
"home", "treat", "confident", "peace", "paper", "custom", "rain", "lucky",
"win", "proud", "beauty", "city", "museum", "success", "laughter", "party",
"key", "justice", "respect", "sorry", "apologize", "kill","help"]
# Regular expression for finding contractions
contractions_re=re.compile('(%s)' % '|'.join(contractions_dict.keys()))
# Function for expanding contractions
def expand_contractions(text,contractions_dict=contractions_dict):
def replace(match):
return contractions_dict[match.group(0)]
return contractions_re.sub(replace, text)
# Preprocessing function
def preprocess_text(text):
# Convert the input to a string
text = str(text)
# Expand contractions
text = expand_contractions(text)
# Remove punctuations
text = re.sub(r'[^\w\s]', '', text)
# Convert to lowercase
text = text.lower()
# If the resulting text is empty, return None
if text == "":
return None
return text
if isinstance(tweets_data, str):
preprocessed_tweets=preprocess_text(tweets_data)
count = 0
for word in absolute_words:
if word in preprocessed_tweets:
count += 1
if count >= 2:
break
return("Depression Detected")
else:
# Apply the preprocess_text function to the tweet df
preprocessed_tweets = tweets_data.apply(preprocess_text)
print(preprocessed_tweets)
# Check if the preprocessed tweets have at least 2 of the absolute words
Early_dep = pd.DataFrame(columns=['Tweets'])
for tweet in preprocessed_tweets:
count = 0
for word in absolute_words:
if word in tweet:
count += 1
if count >= 2:
Early_dep = pd.concat([Early_dep, pd.DataFrame({'Tweets': [tweet]})], ignore_index=True)
break
return(Early_dep)
# Run the app
if __name__ == "__main__":
main()