Update eda.py

eda.py

@@ -8,15 +8,30 @@ def run():
     Function for EDA page
     '''
     st.title('Exploration Data Analysis Section')
-
+# ============================= Showing Data ==========================
+    df = pd.read_csv('Emotion_classify_Data.csv')
+    horizontal_radio_css = 
+    """
+    <style>
+    div.row-widget.stRadio > div{flex-direction:row;}
+    </style>
+    """
+    st.markdown(horizontal_radio_css, unsafe_allow_html=True)
+    data_show = st.radio("**Viewing Options**", ['Top 10 Entries', 'Bottom 10 Entries'])
+    if image_show == 'Top 10 Entries':
+        st.table(df.head(10))
+    else:
+        st.table(df.tail(10))
 # ============================= Simple Analysis ========================
 
     eda=pd.read_csv('eda.csv')
+    
     # basic summary analysis
     emotion_counts = eda['Emotion'].value_counts()
     
     eda['Comment Length'] = eda['Comment'].apply(len)
     eda['Word Count'] = eda['Comment'].apply(lambda x: len(x.split()))
+    
     # emotion distribution
     fig_emotions = px.bar(emotion_counts,
                           x=emotion_counts.index,
@@ -24,7 +39,7 @@ def run():
                           labels={'x': 'Emotion', 'y': 'Count'},
                           title='Distribution of Emotions')
     fig_emotions.update_traces(marker_line_width=1, marker_line_color='black')
-    fig_emotions.update_layout(xaxis_title='Emotions', yaxis_title='Count', width=800)
+    fig_emotions.update_layout(xaxis_title='Emotions', yaxis_title='Count', width=700)
     
     # comment distribution
     fig_comment_length = px.histogram(eda,
@@ -42,9 +57,21 @@ def run():
                                   marginal='box',
                                   title='Distribution of Word Count')
     fig_word_count.update_traces(marker_line_width=1, marker_line_color='black')
-    fig_word_count.update_layout(xaxis_title='Word Count', yaxis_title='Count', width=600)
+    fig_word_count.update_layout(xaxis_title='Word Count', yaxis_title='Count', width=700)
     
     # Display the figures in Streamlit
     st.plotly_chart(fig_emotions)
     st.plotly_chart(fig_comment_length)
     st.plotly_chart(fig_word_count)
+    with st.expander('Explanation'):
+        st.caption(
+            '''
+            The visualization above shows:
+            - The dataset has a balance target class which are `anger, joy, and fear`
+            - The distribution of comment length skewed to the right with the majority of the data is within `30 to 130` comment length
+            - The outliers are the comment lengths that is above `244`
+            - The same goes to the word count, the distribution is skewed to the right with the majority of the data is within the range of `5 to 30` word count
+            - This gives insight about how expressive the people are in the dataset. Most people quite concise but there are a few who's very expressive and open about what they feel.
+            '''
+            )
+# ============================= Word Cloud ==================================