Update app.py

app.py

@@ -5,6 +5,8 @@ import seaborn as sns
 import numpy as np
 from io import StringIO
 import openpyxl
+from st_aggrid import AgGrid, GridUpdateMode
+from st_aggrid.grid_options_builder import GridOptionsBuilder
 
 def load_data(file):
     file_extension = file.name.split('.')[-1].lower()
@@ -24,22 +26,51 @@ def manual_data_entry():
     
     if col_names:
         num_rows = st.number_input("Enter number of rows:", min_value=1, value=5)
-        data = []
-        for i in range(num_rows):
-            row = []
-            for col in col_names:
-                value = st.text_input(f"Enter value for {col} (Row {i+1}):")
-                row.append(value)
-            data.append(row)
+        data = pd.DataFrame(columns=col_names, index=range(num_rows))
         
-        return pd.DataFrame(data, columns=col_names)
+        gd = GridOptionsBuilder.from_dataframe(data)
+        gd.configure_default_column(editable=True)
+        gridoptions = gd.build()
+        
+        grid_table = AgGrid(data, gridOptions=gridoptions, 
+                            update_mode=GridUpdateMode.VALUE_CHANGED, 
+                            height=400)
+        
+        return grid_table['data']
     return None
 
-def perform_analysis(data):
-    st.header("4. Analysis")
+def preprocess_data(data):
+    st.subheader("Data Preprocessing")
+    
+    # Handle missing values
+    if data.isnull().sum().sum() > 0:
+        st.write("Handling missing values:")
+        for column in data.columns:
+            if data[column].isnull().sum() > 0:
+                method = st.selectbox(f"Choose method for {column}:", 
+                                      ["Drop", "Fill with mean", "Fill with median", "Fill with mode"])
+                if method == "Drop":
+                    data = data.dropna(subset=[column])
+                elif method == "Fill with mean":
+                    data[column].fillna(data[column].mean(), inplace=True)
+                elif method == "Fill with median":
+                    data[column].fillna(data[column].median(), inplace=True)
+                elif method == "Fill with mode":
+                    data[column].fillna(data[column].mode()[0], inplace=True)
+    
+    # Convert data types
+    for column in data.columns:
+        if data[column].dtype == 'object':
+            try:
+                data[column] = pd.to_numeric(data[column])
+                st.write(f"Converted {column} to numeric.")
+            except ValueError:
+                st.write(f"Kept {column} as categorical.")
     
-    # EDA
-    st.subheader("Exploratory Data Analysis")
+    return data
+
+def perform_analysis(data):
+    st.header("Exploratory Data Analysis")
     
     # Summary statistics
     st.write("Summary Statistics:")
@@ -70,19 +101,28 @@ def perform_analysis(data):
         sns.histplot(data[column], kde=True, ax=ax)
         st.pyplot(fig)
 
-def main():
-    st.title("PPDAC Data Analysis Toolkit")
+    # Box plots for numerical columns
+    st.write("Box Plots:")
+    for column in numeric_data.columns:
+        fig, ax = plt.subplots()
+        sns.boxplot(data=data, y=column, ax=ax)
+        st.pyplot(fig)
 
-    # Problem
-    st.header("1. Problem")
-    problem = st.text_area("Define your problem:")
+    # Bar plots for categorical columns
+    categorical_columns = data.select_dtypes(include=['object']).columns
+    if not categorical_columns.empty:
+        st.write("Bar Plots for Categorical Variables:")
+        for column in categorical_columns:
+            fig, ax = plt.subplots()
+            data[column].value_counts().plot(kind='bar', ax=ax)
+            plt.title(f"Distribution of {column}")
+            plt.xlabel(column)
+            plt.ylabel("Count")
+            st.pyplot(fig)
 
-    # Plan
-    st.header("2. Plan")
-    plan = st.text_area("Describe your plan:")
+def main():
+    st.title("Interactive EDA Toolkit")
 
-    # Data
-    st.header("3. Data")
     data_input_method = st.radio("Choose data input method:", ("Upload File", "Manual Entry"))
     
     if data_input_method == "Upload File":
@@ -98,18 +138,8 @@ def main():
         st.write("Data Preview:")
         st.write(data.head())
 
-        # Convert columns to numeric where possible
-        for col in data.columns:
-            try:
-                data[col] = pd.to_numeric(data[col])
-            except ValueError:
-                pass  # Keep as non-numeric if conversion fails
-
+        data = preprocess_data(data)
         perform_analysis(data)
 
-        # Conclusion
-        st.header("5. Conclusion")
-        conclusion = st.text_area("Write your conclusion based on the analysis:")
-
 if __name__ == "__main__":
     main()