Spaces:
Sleeping
Sleeping
| #importing the necessary libraries for analysis | |
| import streamlit as st | |
| import pandas as pd | |
| import plotly.express as px | |
| from collections import Counter | |
| #adding the css presentation from the styles file in utils | |
| from utils.styles import load_css | |
| load_css() | |
| #creating the topics and content | |
| st.markdown('<div class="main_title">📊 Analysis of Data</div>', unsafe_allow_html=True) | |
| st.markdown('<div class="feature_text">In our model we label the data we pre-processed the content throught the following steps,</div>', unsafe_allow_html=True) | |
| st.markdown(""" | |
| <div class="feature_text"> | |
| <ul> | |
| <li>Making words lower case</li> | |
| <li>Removing punctuations</li> | |
| <li>Removing stop words</li> | |
| </ul> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| st.markdown('<div class="feature_text">This page highlights the below explanatory data analysis,</div>', unsafe_allow_html=True) | |
| st.markdown(""" | |
| <div class="feature_text"> | |
| <ul> | |
| <li>Length of the normal and pre-processed content</li> | |
| <li>A bar chart of topic distribution</li> | |
| <li>A pie chart of the most frequent words</li> | |
| </ul> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| #dividing the page | |
| st.divider() | |
| #getting the csv file from the classification page | |
| if "uploaded_content" not in st.session_state: | |
| st.warning("Please upload and classify data first.") | |
| st.stop() | |
| uploaded_content = st.session_state["uploaded_content"] | |
| #1.carrying out the text analytics | |
| #creating the lengths | |
| #the normal lengths | |
| word_counts_orig = uploaded_content["content"].astype(str).apply(lambda x: len(x.split())) | |
| mean_orig = word_counts_orig.mean() | |
| max_orig = word_counts_orig.max() | |
| min_orig = word_counts_orig.min() | |
| #the pre-processed lengths | |
| word_counts_new = uploaded_content["pre-processed"].astype(str).apply(lambda x: len(x.split())) | |
| mean_new = word_counts_new.mean() | |
| max_new = word_counts_new.max() | |
| min_new = word_counts_new.min() | |
| #carrying out the text analysis | |
| st.subheader("Text Length Comparison") | |
| with st.container(border=True): | |
| st.markdown("### **Before Pre-Processing**") | |
| c1, c2, c3 = st.columns(3) | |
| c1.metric("Max Words", int(max_orig)) | |
| c2.metric("Min Words", int(min_orig)) | |
| c3.metric("Mean Words", f"{mean_orig:.1f}") | |
| st.divider() | |
| st.markdown("### **After Pre-Processing**") | |
| c4, c5, c6 = st.columns(3) | |
| c4.metric("Max Words", int(max_new)) | |
| c5.metric("Min Words", int(min_new)) | |
| c6.metric("Mean Words", f"{mean_new:.1f}", delta=f"{mean_new - mean_orig:.1f}") | |
| #dividing the page | |
| st.divider() | |
| #2.carrying out the bar chart | |
| st.subheader("Bar Chart of News Topics") | |
| class_counts = uploaded_content["class"].value_counts().reset_index() | |
| class_counts.columns = ['Topics (classes)', 'Number of Articles'] | |
| #creating the bar chart content | |
| fig = px.bar( | |
| class_counts, | |
| x='Topics (classes)', | |
| y='Number of Articles', | |
| text='Number of Articles', | |
| color='Number of Articles', | |
| color_continuous_scale=['#1f4e79', '#f2c94c'], | |
| template='plotly_white' | |
| ) | |
| fig.update_traces(textposition='outside') | |
| fig.update_layout(xaxis_title="<b>Category</b>", yaxis_title="<b>Count</b>", coloraxis_showscale=False) | |
| #displaying the bar chart | |
| st.plotly_chart(fig, use_container_width=True) | |
| st.divider() | |
| #3.carrying out the pie chart | |
| st.subheader("Word Frequency Analysis") | |
| all_words = " ".join(uploaded_content["pre-processed"].astype(str)).split() | |
| word_counts = Counter(all_words).most_common(10) | |
| word_df = pd.DataFrame(word_counts, columns=['Word', 'Frequency']) | |
| #creating the pie chart | |
| fig_pie = px.pie( | |
| word_df, | |
| values='Frequency', | |
| names='Word', | |
| title='', | |
| hole=0.4, | |
| color_discrete_sequence=px.colors.sequential.Blues_r | |
| ) | |
| fig_pie.update_traces(textinfo='percent+label', marker=dict(line=dict(color='#FFFFFF', width=2))) | |
| #displaying the pie chart | |
| st.plotly_chart(fig_pie, use_container_width=True) | |