Update pages/2DATA PROFILER.py

pages/2DATA PROFILER.py

@@ -55,203 +55,205 @@ st.markdown("""
     </style>
     """, unsafe_allow_html=True)
 
-######
-def main():
-    # st.title('PAGE TITLE')  # Change this for each page
-    sidebar()
-########
-    
-    def load_dataframe_to_sqlserver(df, table_name, connection_string):
-        # Establish a connection to the database
-        conn = pyodbc.connect(connection_string)
-        cursor = conn.cursor()
-        
-        # Drop table if it exists
-        drop_table_sql = f"IF OBJECT_ID('{table_name}', 'U') IS NOT NULL DROP TABLE {table_name}"
-        
-        try:
-            cursor.execute(drop_table_sql)
-            conn.commit()
-        except Exception as e:
-            st.error(f"Error dropping table. Please try with a different name.")
-        
-        # Create table SQL statement based on DataFrame columns and types
-        create_table_sql = f"CREATE TABLE {table_name} ("
-        for column in df.columns:
-            dtype = str(df[column].dtype)
-            sql_dtype = 'NVARCHAR(MAX)'
-            create_table_sql += f"{column} {sql_dtype}, "
-        create_table_sql = create_table_sql.rstrip(', ') + ')'
-        
-        try:
-            # Execute table creation
-            cursor.execute(create_table_sql)
-            conn.commit()
-        except Exception as e:
-            st.error(f"Error Creating table. Please try with a different name.")
-    
-        # Insert DataFrame data into the table using bulk insert
-        insert_sql = f"INSERT INTO {table_name} ({', '.join(df.columns)}) VALUES ({', '.join(['?' for _ in df.columns])})"
-        
-        try:
-            # Using `fast_executemany` for bulk inserts
-            cursor.fast_executemany = True
-            cursor.executemany(insert_sql, df.values.tolist())
-            conn.commit()
-            st.success(f"Data Imported with table name: '{table_name}' successfully.")
-        except Exception as e:
-            st.error(f"Error Inserting Data. Please try with a different name.")
-        
-        cursor.close()
-        conn.close()
-        
-    
-    def clear_cache():
-        keys = list(st.session_state.keys())
-        for key in keys:
-            st.session_state.pop(key)
-            
-    def set_bg_hack(main_bg):
-            '''
-            A function to unpack an image from root folder and set as bg.
-         
-            Returns
-            -------
-            The background.
-            '''
-            # set bg name
-            main_bg_ext = "png"
-                
-            st.markdown(
-                 f"""
-                 <style>
-                 .stApp {{
-                     background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()});
-                     background-size: cover
-                 }}
-                 </style>
-                 """,
-                 unsafe_allow_html=True
-             )
-    #set_bg_hack("bg2.png")
-    header_style = """
-        <style>
-            .header {
-                color: black;  /* Soft dark gray text color for readability */
-                width: 103%;
-                font-size: 60px;  /* Large font size */
-                font-weight: bold;  /* Bold text */
-                line-height: 1.2;  /* Improved readability */
-                margin-bottom: 30px;  /* Add some space below the header */
-                padding: 20px;  /* Add padding for better spacing */
-                background-image:
-                    linear-gradient(to right, rgba(255, 140, 0, 0.3) 25%, transparent 75%),  /* Darker orange with higher opacity */
-                    linear-gradient(to bottom, rgba(255, 140, 0, 0.3) 15%, transparent 75%),
-                    linear-gradient(to left, rgba(255, 140, 0, 0.3) 25%, transparent 55%),
-                    linear-gradient(to top, rgba(255, 140, 0, 0.3) 25%, transparent 95%);
-                background-blend-mode: overlay;
-                background-size: 250px 350px;
-                border-radius: 10px;  /* Add border radius for rounded corners */
-                box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);  /* Add shadow for depth */
-            }
-        </style>
-    """
+
+
+def load_dataframe_to_sqlserver(df, table_name, connection_string):
+    # Establish a connection to the database
+    conn = pyodbc.connect(connection_string)
+    cursor = conn.cursor()
     
+    # Drop table if it exists
+    drop_table_sql = f"IF OBJECT_ID('{table_name}', 'U') IS NOT NULL DROP TABLE {table_name}"
     
+    try:
+        cursor.execute(drop_table_sql)
+        conn.commit()
+    except Exception as e:
+        st.error(f"Error dropping table. Please try with a different name.")
     
+    # Create table SQL statement based on DataFrame columns and types
+    create_table_sql = f"CREATE TABLE {table_name} ("
+    for column in df.columns:
+        dtype = str(df[column].dtype)
+        sql_dtype = 'NVARCHAR(MAX)'
+        create_table_sql += f"{column} {sql_dtype}, "
+    create_table_sql = create_table_sql.rstrip(', ') + ')'
     
+    try:
+        # Execute table creation
+        cursor.execute(create_table_sql)
+        conn.commit()
+    except Exception as e:
+        st.error(f"Error Creating table. Please try with a different name.")
+
+    # Insert DataFrame data into the table using bulk insert
+    insert_sql = f"INSERT INTO {table_name} ({', '.join(df.columns)}) VALUES ({', '.join(['?' for _ in df.columns])})"
     
-    content_style = """
-        <style>
-            .content {
-                font-size: 40px;  /* Larger font size for content */
-                line-height: 1.6;  /* Improved readability */
-                width: 103%;
-                padding: 10px;  /* Add padding for better spacing */
-                margin-bottom: 20px;
-                background-color: sky-blue;  /* Background color for the header */
-                border-radius: 10px;  /* Add border radius for rounded corners */
-                box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);  /* Add shadow for depth */
-            }
-        </style>
-    """
+    try:
+        # Using `fast_executemany` for bulk inserts
+        cursor.fast_executemany = True
+        cursor.executemany(insert_sql, df.values.tolist())
+        conn.commit()
+        st.success(f"Data Imported with table name: '{table_name}' successfully.")
+    except Exception as e:
+        st.error(f"Error Inserting Data. Please try with a different name.")
     
-    small_style = """
-        <style>
-            .small {
-                color: black;
-                font-size: 30px;  /* Larger font size for content */
-                line-height: 1.6;  /* Improved readability */
-                width: 100%;
-                padding: 10px;  /* Add padding for better spacing */
-                margin-bottom: 10px;
-                background-color: white;  /* Background color for the header */
-                border-radius: 10px;  /* Add border radius for rounded corners */
-            }
-        </style>
-    """
+    cursor.close()
+    conn.close()
     
-    def update_column_dtype(df, column_name, dtype):
-        error_entries = pd.DataFrame()
-        flag = None
-        if dtype == 'System Detected':
-            pass
-        elif dtype == 'int64':
-            try:
-                df[column_name] = df[column_name].astype('int64')
-            except ValueError:
-                error_entries = df[~df[column_name].apply(lambda x: str(x).isdigit())]
-                st.error('Unable to convert some entries to integer. Please Clean the column.')
-        elif dtype == 'float64/numeric':
-            try:
-                df[column_name] = df[column_name].astype('float64')
-            except ValueError:
-                error_entries = df[pd.to_numeric(df[column_name], errors='coerce').isna()]
-                st.error('Unable to convert some entries to float. Please Clean the column.')
-        elif dtype == 'id':
-            try:
-                df[column_name] = df[column_name].astype('int64')
-            except ValueError:
-                error_entries = df[~df[column_name].apply(lambda x: str(x).isdigit())]
-                st.error('Unable to convert some entries to id. Please Clean the column.')
-        elif dtype == 'categorical/string':
-            df[column_name] = df[column_name].astype('category')
-        elif dtype == 'datetime':
-            try:
-                df[column_name] = pd.to_datetime(df[column_name], errors='raise', infer_datetime_format=True)
-            except ValueError:
-                error_entries = df[pd.to_datetime(df[column_name], errors='coerce', infer_datetime_format=True).isna()]
-                custom_format = st.text_input("Please provide the datetime format (e.g., %Y-%m-%d):")
-                if custom_format:
-                    try:
-                        df[column_name] = pd.to_datetime(df[column_name], errors='raise', format=custom_format)
-                    except ValueError:
-                        error_entries = df[pd.to_datetime(df[column_name], errors='coerce', format=custom_format).isna()]
-                        st.error('Unable to parse datetime with the provided format. Please Clean the column.')
-        elif dtype == 'email':
-            df[column_name] = df[column_name].astype('category')
-            flag= 'email'
-        elif dtype == 'phone_number':
-            df[column_name] = df[column_name].astype('category')
-            flag= 'phone_number'
+
+def clear_cache():
+    keys = list(st.session_state.keys())
+    for key in keys:
+        st.session_state.pop(key)
         
-        return df, error_entries, flag
+def set_bg_hack(main_bg):
+        '''
+        A function to unpack an image from root folder and set as bg.
+     
+        Returns
+        -------
+        The background.
+        '''
+        # set bg name
+        main_bg_ext = "png"
+            
+        st.markdown(
+             f"""
+             <style>
+             .stApp {{
+                 background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()});
+                 background-size: cover
+             }}
+             </style>
+             """,
+             unsafe_allow_html=True
+         )
+#set_bg_hack("bg2.png")
+header_style = """
+    <style>
+        .header {
+            color: black;  /* Soft dark gray text color for readability */
+            width: 103%;
+            font-size: 60px;  /* Large font size */
+            font-weight: bold;  /* Bold text */
+            line-height: 1.2;  /* Improved readability */
+            margin-bottom: 30px;  /* Add some space below the header */
+            padding: 20px;  /* Add padding for better spacing */
+            background-image:
+                linear-gradient(to right, rgba(255, 140, 0, 0.3) 25%, transparent 75%),  /* Darker orange with higher opacity */
+                linear-gradient(to bottom, rgba(255, 140, 0, 0.3) 15%, transparent 75%),
+                linear-gradient(to left, rgba(255, 140, 0, 0.3) 25%, transparent 55%),
+                linear-gradient(to top, rgba(255, 140, 0, 0.3) 25%, transparent 95%);
+            background-blend-mode: overlay;
+            background-size: 250px 350px;
+            border-radius: 10px;  /* Add border radius for rounded corners */
+            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);  /* Add shadow for depth */
+        }
+    </style>
+"""
+
+
+
+
+
+content_style = """
+    <style>
+        .content {
+            font-size: 40px;  /* Larger font size for content */
+            line-height: 1.6;  /* Improved readability */
+            width: 103%;
+            padding: 10px;  /* Add padding for better spacing */
+            margin-bottom: 20px;
+            background-color: sky-blue;  /* Background color for the header */
+            border-radius: 10px;  /* Add border radius for rounded corners */
+            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);  /* Add shadow for depth */
+        }
+    </style>
+"""
+
+small_style = """
+    <style>
+        .small {
+            color: black;
+            font-size: 30px;  /* Larger font size for content */
+            line-height: 1.6;  /* Improved readability */
+            width: 100%;
+            padding: 10px;  /* Add padding for better spacing */
+            margin-bottom: 10px;
+            background-color: white;  /* Background color for the header */
+            border-radius: 10px;  /* Add border radius for rounded corners */
+        }
+    </style>
+"""
+
+def update_column_dtype(df, column_name, dtype):
+    error_entries = pd.DataFrame()
+    flag = None
+    if dtype == 'System Detected':
+        pass
+    elif dtype == 'int64':
+        try:
+            df[column_name] = df[column_name].astype('int64')
+        except ValueError:
+            error_entries = df[~df[column_name].apply(lambda x: str(x).isdigit())]
+            st.error('Unable to convert some entries to integer. Please Clean the column.')
+    elif dtype == 'float64/numeric':
+        try:
+            df[column_name] = df[column_name].astype('float64')
+        except ValueError:
+            error_entries = df[pd.to_numeric(df[column_name], errors='coerce').isna()]
+            st.error('Unable to convert some entries to float. Please Clean the column.')
+    elif dtype == 'id':
+        try:
+            df[column_name] = df[column_name].astype('int64')
+        except ValueError:
+            error_entries = df[~df[column_name].apply(lambda x: str(x).isdigit())]
+            st.error('Unable to convert some entries to id. Please Clean the column.')
+    elif dtype == 'categorical/string':
+        df[column_name] = df[column_name].astype('category')
+    elif dtype == 'datetime':
+        try:
+            df[column_name] = pd.to_datetime(df[column_name], errors='raise', infer_datetime_format=True)
+        except ValueError:
+            error_entries = df[pd.to_datetime(df[column_name], errors='coerce', infer_datetime_format=True).isna()]
+            custom_format = st.text_input("Please provide the datetime format (e.g., %Y-%m-%d):")
+            if custom_format:
+                try:
+                    df[column_name] = pd.to_datetime(df[column_name], errors='raise', format=custom_format)
+                except ValueError:
+                    error_entries = df[pd.to_datetime(df[column_name], errors='coerce', format=custom_format).isna()]
+                    st.error('Unable to parse datetime with the provided format. Please Clean the column.')
+    elif dtype == 'email':
+        df[column_name] = df[column_name].astype('category')
+        flag= 'email'
+    elif dtype == 'phone_number':
+        df[column_name] = df[column_name].astype('category')
+        flag= 'phone_number'
     
-    def convert_to_special_representation(value):
-        value = str(value)
-        special_chars = set("!@#$%^&*()_+-=[]{}|;:,.<>?`~")
-        result = ''
-        for char in value:
-            if char.isdigit():
-                result += 'N'
-            elif char.isalpha():
-                result += 'A'
-            elif char in special_chars:
-                result += char
-            else:
-                # Handle other characters as needed
-                result += char
-        return result
+    return df, error_entries, flag
+
+def convert_to_special_representation(value):
+    value = str(value)
+    special_chars = set("!@#$%^&*()_+-=[]{}|;:,.<>?`~")
+    result = ''
+    for char in value:
+        if char.isdigit():
+            result += 'N'
+        elif char.isalpha():
+            result += 'A'
+        elif char in special_chars:
+            result += char
+        else:
+            # Handle other characters as needed
+            result += char
+    return result
+
+######
+def main():
+    # st.title('PAGE TITLE')  # Change this for each page
+    sidebar()
+########
     with st.container(border=True):
         st.subheader('SELECT TABLE')    
         metadata = SingleTableMetadata()