Spaces:
Runtime error
Runtime error
File size: 3,394 Bytes
cdfa715 013f8ea cdfa715 013f8ea ec3726f cdfa715 09ae9ce 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 013f8ea cdfa715 |
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 |
import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import nltk
from sklearn.feature_extraction.text import CountVectorizer
import re
from nltk.corpus import stopwords
from nltk.stem import SnowballStemmer
# Download NLTK punkt tokenizer and stopwords
nltk.download('punkt')
nltk.download('stopwords')
# Function to preprocess text
def preprocess_text(text):
# Convert text to lowercase
text = text.lower()
# Remove URLs
text = re.sub(r'http\S+', '', text)
# Remove @ mentions
text = re.sub(r'@\S+', '', text)
# Remove hashtags
text = re.sub(r'#\S+', '', text)
# Remove non-alphabetic characters
text = re.sub(r'[^a-zA-Z]', ' ', text)
# Tokenize text
tokens = nltk.word_tokenize(text)
# Remove stopwords
stop_words = set(stopwords.words('english'))
filtered_tokens = [word for word in tokens if word not in stop_words]
# Stemming
stemmer = SnowballStemmer('english')
stemmed_tokens = [stemmer.stem(word) for word in filtered_tokens]
# Join tokens into a single string
processed_text = ' '.join(stemmed_tokens)
return processed_text
# Function to load and preprocess DataFrame
def load_and_preprocess_dataframe(file_path):
dataframe = pd.read_csv(file_path)
dataframe['processed_text'] = dataframe['text'].apply(preprocess_text)
return dataframe
# Function to create Document-Term Matrix (DTM)
def create_dtm(dataframe):
vectorizer = CountVectorizer()
dtm = vectorizer.fit_transform(dataframe['processed_text'])
return dtm, vectorizer
# Function to plot word frequency
def plot_word_frequency(dtm, vectorizer):
# Sum word frequencies
word_freq = dtm.sum(axis=0)
words = vectorizer.get_feature_names_out()
# Create DataFrame
word_freq_df = pd.DataFrame({'word': words, 'frequency': np.ravel(word_freq)})
# Sort by frequency
word_freq_df = word_freq_df.sort_values(by='frequency', ascending=False)
# Plot
plt.figure(figsize=(10, 6))
sns.barplot(x='word', y='frequency', data=word_freq_df.head(20))
plt.title('Top 20 Words Frequency')
plt.xlabel('Words')
plt.ylabel('Frequency')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
st.pyplot()
# Streamlit app
def main():
st.title("Tweet Data Analysis")
st.sidebar.header("Upload CSV file")
uploaded_file = st.sidebar.file_uploader("Choose a CSV file", type="csv")
if uploaded_file is not None:
st.sidebar.success('File uploaded successfully!')
st.sidebar.markdown("### Preprocessing Options")
preprocess_checkbox = st.sidebar.checkbox("Preprocess DataFrame")
# Load DataFrame
df = pd.read_csv(uploaded_file)
if preprocess_checkbox:
# Preprocess DataFrame
df['processed_text'] = df['text'].apply(preprocess_text)
st.subheader("Preprocessed DataFrame")
st.write(df.head())
# Create DTM
st.subheader("Document-Term Matrix (DTM)")
dtm, vectorizer = create_dtm(df)
st.write(dtm)
# Plot word frequency
st.subheader("Word Frequency Plot")
plot_word_frequency(dtm, vectorizer)
else:
st.subheader("Original DataFrame")
st.write(df.head())
if __name__ == "__main__":
main()
|