""" Session 1 - First Analysis in VS Code ====================================== File : Session1-First-Analysis-V02.py Author : (your name) Version : V02 Date : 2026-05-13 Objective --------- Load a CSV file from the same folder as this script, compute basic descriptive statistics (mean, standard deviation) and the Pearson correlation between Height and Weight, then save the results to a new CSV file in the same folder. Expected Folder Layout ---------------------- Chapter-01-First-Analysis/ Height-Weight.csv <- Input data (must exist before running) Session1-First-Analysis-V02.py <- This script Summary-Session-V02.csv <- Output produced by this script Required Input File (Height-Weight.csv) ---------------------------------------- Name,Height_cm,Weight_kg Ali,175,70 Sara,160,55 John,180,75 Mei,165,60 Luis,170,68 Column names must match exactly: - Height_cm (numeric, centimetres) - Weight_kg (numeric, kilograms) Quick Start ----------- 1. Open VS Code and open the Chapter-01-First-Analysis folder. 2. Open Session1-First-Analysis-V02.py in the editor. 3. Run the script (Ctrl+F5, or right-click -> Run Python File in Terminal). 4. Read the console output for a preview and computed statistics. 5. Open Summary-Session-V02.csv in the same folder to inspect saved results. Step-by-Step Flow ----------------- Step 1 : Reconfigure stdout/stderr to UTF-8 so special characters print correctly. Step 2 : Import required libraries: sys, os, pandas. Step 3 : Define the input CSV filename and resolve its full path. Step 4 : Load the CSV into a pandas DataFrame. Step 5 : Print the first five rows as a quick data preview. Step 6 : Compute mean and standard deviation for Height_cm and Weight_kg. Step 7 : Print the summary statistics to the console. Step 8 : Compute the Pearson correlation coefficient between the two columns. Step 9 : Print the correlation value to the console. Step 10 : Assemble all results into a small summary DataFrame. Step 11 : Save the summary DataFrame to Summary-Session-V02.csv. Step 12 : Print a success message showing the output file path. Output File (Summary-Session-V02.csv) --------------------------------------- Metric,Value Mean Height, Std Height, Mean Weight, Std Weight, Correlation, Notes ----- - Column names Height_cm and Weight_kg are case-sensitive. Update them at the top of the script if your CSV uses different names. - Pearson correlation ranges from -1 (perfect negative) to +1 (perfect positive). A value near 1.0 means taller people tend to weigh more in this dataset. - The script auto-installs pandas if it is not already present. - UTF-8 reconfiguration lines at the top prevent garbled output on Windows. """ # =========================================================================== # Step 1 - Reconfigure stdout and stderr to UTF-8 # Prevents garbled or missing characters on Windows terminals. # =========================================================================== import sys if hasattr(sys.stdout, 'reconfigure'): # Only available in Python 3.7+ sys.stdout.reconfigure(encoding='utf-8') if hasattr(sys.stderr, 'reconfigure'): sys.stderr.reconfigure(encoding='utf-8') # =========================================================================== # Step 2 - Import standard libraries # =========================================================================== import os # Used to build cross-platform file paths # --------------------------------------------------------------------------- # Step 2b - Import pandas (auto-install if missing) # pandas provides the DataFrame structure used throughout this script. # --------------------------------------------------------------------------- try: import pandas as pd except ImportError: print('[INFO] pandas not found. Attempting automatic install...') import subprocess subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'pandas']) import pandas as pd # Re-import after installation print('[INFO] pandas installed successfully.') # =========================================================================== # Step 3 - Define file paths # Both input and output files sit in the same folder as this script. # Using os.path.dirname(__file__) makes this portable across machines. # =========================================================================== SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__)) # Folder of this .py file INPUT_FILE = 'Height-Weight.csv' # Input CSV filename OUTPUT_FILE = 'Summary-Session-V01.csv' # Output CSV filename input_path = os.path.join(SCRIPT_DIR, INPUT_FILE) # Full path to input output_path = os.path.join(SCRIPT_DIR, OUTPUT_FILE) # Full path to output print(f'[DEBUG] Script folder : {SCRIPT_DIR}') print(f'[DEBUG] Input file : {input_path}') print(f'[DEBUG] Output file : {output_path}') # =========================================================================== # Step 4 - Load the CSV file into a pandas DataFrame # encoding='utf-8' handles accented characters in names. # If the file is missing, pandas raises a clear FileNotFoundError. # =========================================================================== print('\n[INFO] Loading data from CSV...') df = pd.read_csv(input_path, encoding='utf-8') # df = main data table print(f'[DEBUG] Rows loaded: {len(df)} | Columns: {list(df.columns)}') # =========================================================================== # Step 5 - Print a quick data preview (first 5 rows) # =========================================================================== print('\n=== Data Preview (first 5 rows) ===') print(df.head()) # Shows up to 5 rows # =========================================================================== # Step 6 - Compute descriptive statistics for Height and Weight # .mean() -> arithmetic average # .std() -> sample standard deviation (ddof=1 by default in pandas) # =========================================================================== mean_height = df['Height_cm'].mean() # Average height across all rows mean_weight = df['Weight_kg'].mean() # Average weight across all rows std_height = df['Height_cm'].std() # Spread / variability of height values std_weight = df['Weight_kg'].std() # Spread / variability of weight values # =========================================================================== # Step 7 - Print the summary statistics # =========================================================================== print('\n=== Summary Statistics ===') print(f' Average Height : {mean_height:.1f} cm') print(f' Std Dev Height : {std_height:.1f} cm') print(f' Average Weight : {mean_weight:.1f} kg') print(f' Std Dev Weight : {std_weight:.1f} kg') # =========================================================================== # Step 8 - Compute Pearson correlation coefficient # Measures the linear relationship between Height_cm and Weight_kg. # Value of 1.0 -> perfect positive correlation (taller = heavier) # Value of 0.0 -> no linear relationship # Value of -1.0 -> perfect negative correlation (taller = lighter) # =========================================================================== corr = df['Height_cm'].corr(df['Weight_kg']) # Pearson r (default method) # =========================================================================== # Step 9 - Print the correlation value # =========================================================================== print(f'\n Pearson Correlation (Height vs Weight) : {corr:.2f}') # Quick interpretation hint printed to console if corr >= 0.8: print(' [INFO] Strong positive correlation.') elif corr >= 0.5: print(' [INFO] Moderate positive correlation.') elif corr >= 0.0: print(' [INFO] Weak or no positive correlation.') else: print(' [INFO] Negative correlation detected.') # =========================================================================== # Step 10 - Assemble results into a compact summary DataFrame # Two columns: Metric (label) and Value (number) # =========================================================================== summary = pd.DataFrame({ 'Metric': [ 'Mean Height (cm)', 'Std Dev Height (cm)', 'Mean Weight (kg)', 'Std Dev Weight (kg)', 'Pearson Correlation', ], 'Value': [ round(mean_height, 4), round(std_height, 4), round(mean_weight, 4), round(std_weight, 4), round(corr, 4), ] }) print('\n=== Results Table ===') print(summary.to_string(index=False)) # Print without row numbers # =========================================================================== # Step 11 - Save the summary DataFrame to a CSV file # index=False omits the automatic row-number column. # =========================================================================== summary.to_csv(output_path, index=False, encoding='utf-8') # =========================================================================== # Step 12 - Print success message with the output file location # =========================================================================== print(f'\n[DONE] Results saved to: {output_path}') print(f'\npay attention the input and output are both are in the code folder') print(f'In future sessions we will use') print(f'A-Data - Where are input data files are stored') print(f'B-Engines - Where are python code is stored') print(f'C-Results - Where the results of the program are stored')