# First, let us check our Python version.
import sys
print('Python version:', sys.version)
 
 

# Let us make a sample CSV file right in Python.
with open('sample.csv', 'w') as f:
    f.write('name,age,city\n')
    f.write('Anna,23,New York\n')
    f.write('Ben,31,London\n')
    f.write('Clara,27,Paris\n')
 
# Now we have a sample.csv file to try out.
 
 

# Reading a CSV file using Python's built-in csv module
import csv

with open('sample.csv', 'r') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)
 
 

# Reading the CSV file as dictionaries (easier to access by column name)
with open('sample.csv', 'r') as file:
    reader = csv.DictReader(file)
    for row in reader:
        print(row['name'], row['city'])
 
 

# Handling missing values in CSV files
with open('sample.csv', 'r') as file:
    reader = csv.DictReader(file)
    for row in reader:
        name = row.get('name', 'Unknown')
        age = row.get('age', 'N/A')
        city = row.get('city', 'Somewhere')
        print(f'{name} is {age} years old and lives in {city}.')
 
 

# Let us read a CSV file using pandas, a popular data library.
import pandas as pd
df = pd.read_csv('sample.csv')
print(df)
 
 

# What if the column names are missing or wrong? Let us set them ourselves.
columns = ['Person', 'Years', 'Location']
df2 = pd.read_csv('sample.csv', names=columns, header=0)
print(df2)
 
 

# Let us load only certain columns from a bigger CSV file.
columns_to_use = ['name', 'city']
df_small = pd.read_csv('sample.csv', usecols=columns_to_use)
print(df_small)
 
 

# Let us save the table we made in pandas to a new Excel file.
df.to_excel('sample_data.xlsx', index=False)
print('Excel file saved!')
 
 

# Let us read our new Excel file with pandas.
excel_df = pd.read_excel('sample_data.xlsx')
print(excel_df)
 
 

# What if your Excel file has more than one sheet?
sheetnames = pd.ExcelFile('sample_data.xlsx').sheet_names
print('Sheets in this file:', sheetnames)
 
multi_sheet_df = pd.read_excel('sample_data.xlsx', sheet_name=sheetnames[0])
print(multi_sheet_df)
 
 

# Let us make a small example JSON file.
import json
data = [
    {'name':'Anna', 'age':23, 'pets':['cat','dog']},
    {'name':'Ben', 'age':31, 'pets':[]},
    {'name':'Clara', 'age':27, 'pets':['parrot']},
]
with open('sample.json', 'w') as f:
    json.dump(data, f)
 
 

# Let us read our JSON file back into Python.
with open('sample.json', 'r') as f:
    info = json.load(f)
    for person in info:
        print(person['name'], 'has pets:', person['pets'])
 
 

# pandas can also load JSON as a table
json_df = pd.read_json('sample.json')
print(json_df)
 
 

# What if your JSON file has nested dictionaries? Let us practice safe access.
data_nested = [
    {'id':101, 'details':{'name':'Dana', 'age':22}},
    {'id':102, 'details':{'name':'Eli'}},
    {'id':103, 'details':{}}
]
with open('nested.json', 'w') as f:
    json.dump(data_nested, f)
 
with open('nested.json') as f:
    nested = json.load(f)
    for row in nested:
        name = row.get('details', {}).get('name', 'Unknown')
        age = row.get('details', {}).get('age', 'N/A')
        print(f'ID {row['id']}: {name} ({age})')
 
 

# Mini-project: Ask the user for a file type then read and print the data.
ftype = input('Which file type do you want to open? (csv, excel, json): ').strip().lower()
result = None

if ftype == 'csv':
    result = pd.read_csv('sample.csv')
elif ftype == 'excel':
    result = pd.read_excel('sample_data.xlsx')
elif ftype == 'json':
    result = pd.read_json('sample.json')
else:
    print('Unknown file type. Please enter csv, excel, or json.')

if result is not None:
    print(result)
 
 

# Extra tip: How to see the first few rows of big data.
df = pd.read_csv('sample.csv')
print(df.head(2))
 
 

# Troubleshooting: What if you get a FileNotFoundError?
try:
    pd.read_csv('missing.csv')
except FileNotFoundError:
    print('Could not find that file. Check the file name or path.')