Update pages/2_Simple_EDA.py

pages/2_Simple_EDA.py

@@ -3,112 +3,102 @@ import pandas as pd
 import io
 
 st.markdown("""
-    <style>
-        .title-container {
-            text-align: center;
-            margin-bottom: 20px;
-        }
-        .main-title {
-            color: #c71585;
-            font-size: 36px;
-            font-weight: bold;
-        }
-        .subtitle {
-            color: #4F4F4F;
-            font-size: 20px;
-            font-weight: normal;
-        }
-        .section-title {
-            color: #2a52be;
-            font-size: 24px;
-            font-weight: bold;
-            margin-top: 20px;
-        }
-        .highlight {
-            background-color: #f8f8f8;
-            padding: 10px;
-            border-radius: 5px;
-            font-size: 14px;
-            font-family: monospace;
-        }
-    </style>
-""", unsafe_allow_html=True)
-
-st.markdown("""
-    <div class="title-container">
-        <h2 class="main-title">Simple EDA: Understanding Your Data🔍</h2>
-        <h3 class="subtitle">This helps us understand the quality of the data and see how the data looks.</h3>
+    <div style="text-align: center; margin-bottom: 20px;">
+        <h2 style="color: #c71585; font-size: 36px;">Simple EDA: Understanding Your Data🔍</h1>
+        <h3 style="color: #4F4F4F; font-size: 20px;">
+            This helps us understand the quality of the data and see how the data looks.
+        </h3>
     </div>
 """, unsafe_allow_html=True)
 
 if "df" in st.session_state and st.session_state.df is not None:
     df = st.session_state.df
 
-    st.markdown("<h3 class='section-title'>Dataset Preview📌</h3>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #2a52be;'>Dataset Preview📌</h3>", unsafe_allow_html=True)
     st.dataframe(df.head())
     
-    st.markdown("<h3 class='section-title'>Dataset Shape</h3>", unsafe_allow_html=True)
+
+    st.markdown("<h3 style='color: #843f5b;'>Dataset Shape</h3>", unsafe_allow_html=True)
     st.write(f"🔹 The dataset contains **{df.shape[0]} rows** and **{df.shape[1]} columns**.")
-    
-    st.markdown("<h3 class='section-title'>Column Names & Data Types</h3>", unsafe_allow_html=True)
+
+    st.markdown("<h3 style='color: #e25822;'>Column Names & Data Types</h3>", unsafe_allow_html=True)
     st.write(df.dtypes)
 
-    st.markdown("<h3 class='section-title'>Dataset Information📝</h3>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #9400d3;'>Dataset Information📝</h3>", unsafe_allow_html=True)
+    
     buffer = io.StringIO()
     df.info(buf=buffer)
     info_str = buffer.getvalue()
-    st.markdown(f"<pre class='highlight'>{info_str}</pre>", unsafe_allow_html=True)
+    st.text(info_str)
 
-    st.markdown("<h3 class='section-title'>Numerical and Categorical Columns</h3>", unsafe_allow_html=True)
+    st.markdown(f"<pre style='background-color: #f8f8f8; padding: 10px; border-radius: 5px; font-size: 14px; font-family: monospace;'>{info_str}</pre>", unsafe_allow_html=True)
+
+
+    st.markdown("<h3 style='color: #9400d3;'>Numerical and Categorical Columns</h3>", unsafe_allow_html=True)
+    
     numerical_cols = df.select_dtypes(include=['int64', 'float64']).columns.tolist()
     categorical_cols = df.select_dtypes(include=['object', 'category']).columns.tolist()
     
     st.write(f"🔹 **Numerical Columns ({len(numerical_cols)}):** {', '.join(numerical_cols) if numerical_cols else 'None'}")
     st.write(f"🔹 **Categorical Columns ({len(categorical_cols)}):** {', '.join(categorical_cols) if categorical_cols else 'None'}")
 
-    st.markdown("<h3 class='section-title'>Unique Values in Categorical Columns</h3>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #e25822;'>Unique Values in Categorical Columns</h3>", unsafe_allow_html=True)
+    
     if categorical_cols:
         for col in categorical_cols:
-            st.write(f"**{col}:** {df[col].nunique()} unique values")
+            unique_count = df[col].nunique()
+            st.write(f"**{col}:** {unique_count} unique values")
     else:
         st.info("No categorical columns detectedℹ️.")
     
-    st.markdown("<h3 class='section-title'>Value Counts in Categorical Columns</h3>", unsafe_allow_html=True)
+    # Value Counts in Categorical Columns
+    st.markdown("<h3 style='color: #9400d3;'>Value Counts in Categorical Columns</h3>", unsafe_allow_html=True)
+    
     if categorical_cols:
         for col in categorical_cols:
             st.write(f"🔹 **{col} Value Distribution:**")
-            st.write(df[col].value_counts().head(10))  
+            st.write(df[col].value_counts().head(10))  # Show top 10 categories
     else:
         st.info("No categorical columns detectedℹ️.")
-        
-    st.markdown("<h3 class='section-title'>Summary Statistics for Numerical Columns</h3>", unsafe_allow_html=True)
+
+
+    st.markdown("<h3 style='color: #843f5b;'>Summary Statistics for Numerical Columns</h3>", unsafe_allow_html=True)
+    
+    st.write("🔹 **Basic statistical insights into the dataset:**")
     st.write(df.describe())
+
+    st.markdown("<h3 style='color: #2a52be;'>Summary Statistics for Categorical Columns</h3>", unsafe_allow_html=True)
     
-    st.markdown("<h3 class='section-title'>Summary Statistics for Categorical Columns</h3>", unsafe_allow_html=True)
     if categorical_cols:
         st.write(df[categorical_cols].describe(include='object'))
     else:
         st.info("No categorical columns detectedℹ️.")
-    
-    st.markdown("<h3 class='section-title'>Missing Values in the Dataset⚠️</h3>", unsafe_allow_html=True)
+
+    st.markdown("<h3 style='color: #9400d3;'>Missing Values in the Dataset⚠️</h3>", unsafe_allow_html=True)
     missing_values = df.isnull().sum()
+    
     if missing_values.sum() == 0:
         st.success("No missing values found!")
     else:
-        st.warning("Found missing values in the dataset.")
+        st.warning(f"Found missing values in the dataset.")
+        st.write("🔹 **Columns with Missing Values:**")
         st.write(missing_values[missing_values > 0])
 
-    st.markdown("<h3 class='section-title'>Duplicate Records</h3>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #2a52be;'>Duplicate Records</h3>", unsafe_allow_html=True)
     duplicate_count = df.duplicated().sum()
+    
     if duplicate_count == 0:
         st.success("No duplicate records found!")
     else:
         st.warning(f"Found {duplicate_count} duplicate rows in the dataset.")
+        st.write("🔹 **Example Duplicate Rows:**")
         st.dataframe(df[df.duplicated()].head())
 
-    st.markdown("<h3 class='section-title'>Outlier Detection</h3>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #e25822;'>Outlier Detection</h3>", unsafe_allow_html=True)
+    
     if numerical_cols:
         outlier_info = {}
+        
         for col in numerical_cols:
             Q1 = df[col].quantile(0.25)
             Q3 = df[col].quantile(0.75)
@@ -116,8 +106,10 @@ if "df" in st.session_state and st.session_state.df is not None:
             lower_bound = Q1 - 1.5 * IQR
             upper_bound = Q3 + 1.5 * IQR
             outliers = ((df[col] < lower_bound) | (df[col] > upper_bound)).sum()
+            
             if outliers > 0:
                 outlier_info[col] = outliers
+    
         if outlier_info:
             st.warning("Outliers detected:")
             for col, count in outlier_info.items():
@@ -126,5 +118,7 @@ if "df" in st.session_state and st.session_state.df is not None:
             st.success("No significant outliers detected!")
     else:
         st.info("No numerical columns detectedℹ️.")
+
+
 else:
     st.warning("No dataset found! Please upload a dataset first⚠️.")