Update pages/6.Data Collection.py

pages/6.Data Collection.py

@@ -21,4 +21,105 @@ if data_type == "Structured":
     format_selected = st.radio(
         "Select a data format to learn more:", ["Excel", "CSV", "SQL Databases"]
     )
-    
+
+  # Excel Format Section
+    if format_selected == "Excel":
+        st.write("#### Excel Format")
+
+        # Part (a) What it is
+        st.subheader("What is Excel?")
+        st.write("""
+        Excel is a popular file format used for storing structured data in tabular form.
+        It is commonly used in business and data analysis, and its file extensions include `.xlsx` and `.xls`.
+        """)
+
+        # Part (b) How to read these files
+        st.subheader("How to Read Excel Files?")
+        st.code("""
+        import pandas as pd
+        # Read an Excel file
+        df = pd.read_excel("file.xlsx")
+        print(df.head())
+        """)
+
+        # Part (c) Issues encountered
+        st.subheader("Common Issues Encountered When Handling Excel Files")
+        st.write("""
+        - **Missing Data**: Some cells may contain empty or null values.
+        - **Encoding Problems**: Files saved in non-standard formats may have encoding issues.
+        - **File Corruption**: The file may become unreadable if improperly saved or transferred.
+        - **Large Files**: Handling very large Excel files may exceed memory limits.
+        """)
+
+        # Part (d) How to overcome these errors/issues
+        st.subheader("How to Overcome These Issues?")
+        st.write("""
+        - **Missing Data**: Use data imputation techniques to fill in missing values.
+        - **Encoding Problems**: Specify the encoding format when reading the file, e.g., `encoding='utf-8'`.
+        - **File Corruption**: Use repair tools or convert to a compatible format like CSV.
+        - **Large Files**: Process the file in chunks using `pandas` or optimize it using external tools.
+        """)
+
+        # Downloadable Guide Button
+        st.markdown("### Download Coding Guide:")
+        if st.button("Download Excel Guide"):
+            # Provide a downloadable file
+            file_path = "Excel_guide.ipynb"  # Ensure this file exists in the app directory
+            with open(file_path, "rb") as file:
+                st.download_button(
+                    label="Download Excel Guide",
+                    data=file,
+                    file_name="Excel_guide.ipynb",
+                    mime="application/octet-stream",
+                )
+
+        # CSV Format Section
+        elif format_selected == "CSV":
+        st.write("#### CSV Format")
+
+        # Part (a) What it is
+        st.subheader("What is CSV?")
+        st.write("""
+        CSV (Comma-Separated Values) is a lightweight text file format for structured data,
+        where values are separated by commas. It is widely used for data exchange between systems.
+        """)
+
+        # Part (b) How to read these files
+        st.subheader("How to Read CSV Files?")
+        st.code("""
+        import pandas as pd
+        # Read a CSV file
+        df = pd.read_csv("file.csv")
+        print(df.head())
+        """)
+
+        # Part (c) Issues encountered
+        st.subheader("Common Issues Encountered When Handling CSV Files")
+        st.write("""
+        - **Misaligned Rows**: Extra or missing delimiters can lead to misaligned rows.
+        - **Encoding Problems**: Non-standard characters may cause encoding errors.
+        - **Large Files**: Processing large CSV files can be resource-intensive.
+        """)
+
+        # Part (d) How to overcome these errors/issues
+        st.subheader("How to Overcome These Issues?")
+        st.write("""
+        - **Misaligned Rows**: Use a consistent delimiter and validate the file before processing.
+        - **Encoding Problems**: Explicitly specify the encoding format, e.g., `encoding='utf-8'`.
+        - **Large Files**: Process the file in chunks using `pandas` (`chunksize` parameter).
+        """)
+
+        # Downloadable Guide Button
+        st.markdown("### Download Coding Guide:")
+        if st.button("Download CSV Guide"):
+            # Provide a downloadable file
+            file_path = "CSV_guide.ipynb"  # Ensure this file exists in the app directory
+            with open(file_path, "rb") as file:
+                st.download_button(
+                    label="Download CSV Guide",
+                    data=file,
+                    file_name="CSV_guide.ipynb",
+                    mime="application/octet-stream",
+                )
+
+# Add similar sections for "Unstructured" and "Semi-Structured" data types as needed.