Week 2: Data Structures and File Handling

# Creating lists
exam_scores = [72, 88, 65, 91, 78, 55, 83, 90, 67, 74]
student_names = ["Amara", "Emeka", "Ngozi", "Tunde", "Aisha"]
mixed_list = [1, "two", 3.0, True, None]  # lists can mix types

# Length
print(f"Number of students: {{len(exam_scores)}}")   # 10

# Indexing - Python counts from 0
print(exam_scores[0])    # 72 (first item)
print(exam_scores[-1])   # 74 (last item - negative indexing)
print(exam_scores[2])    # 65 (third item)

# Slicing: list[start:stop:step] - stop is EXCLUDED
print(exam_scores[0:5])   # [72, 88, 65, 91, 78]  first 5
print(exam_scores[5:])    # [55, 83, 90, 67, 74]  from index 5 to end
print(exam_scores[:3])    # [72, 88, 65]           first 3
print(exam_scores[::2])   # [72, 65, 78, 83, 67]  every other item
print(exam_scores[::-1])  # reversed list

# Key list methods
scores = [72, 88, 65, 91, 78]

scores.append(84)         # add one item to end → [72, 88, 65, 91, 78, 84]
scores.extend([77, 95])   # add multiple items   → [..., 84, 77, 95]
scores.insert(0, 100)     # insert at index 0    → [100, 72, 88, ...]
scores.remove(65)         # remove first occurrence of 65
popped = scores.pop()     # remove and return last item
popped2 = scores.pop(0)   # remove and return item at index 0

scores.sort()             # sort in place (ascending)
scores.sort(reverse=True) # sort descending
sorted_copy = sorted(scores)  # returns NEW sorted list, original unchanged

print(f"Max score: {{max(scores)}}")
print(f"Min score: {{min(scores)}}")
print(f"Total: {{sum(scores)}}")
print(f"Mean: {{sum(scores)/len(scores):.1f}}")
print(f"Score 88 appears {{scores.count(88)}} times")
print(f"Index of max: {{scores.index(max(scores))}}")

# Tuples for fixed data
ibadan_coords = (7.3775, 3.9470)     # latitude, longitude
rgb_teal = (0, 196, 167)              # CSS colour
student_record = ("P001", "Amara Okafor", "Statistics", 3.85)

# Unpacking - assign tuple elements to variables
lat, lon = ibadan_coords
print(f"Ibadan: {{lat}}°N, {{lon}}°E")

name, dept, gpa = ("Emeka", "Computer Science", 3.72)

# Tuples as dictionary keys (lists cannot be keys)
coordinates = {{
    (7.3775, 3.9470): "Ibadan",
    (6.5244, 3.3792): "Lagos",
    (9.0579, 7.4951): "Abuja"
}}

# Why use tuple instead of list?
# 1. Signals to readers: this data should not change
# 2. Slightly faster access than lists
# 3. Can be used as dictionary keys
# 4. Functions can return multiple values as tuples
def get_stats(data):
    return min(data), max(data), sum(data)/len(data)   # returns tuple

low, high, avg = get_stats([72, 88, 65, 91])
print(f"Low: {{low}}  High: {{high}}  Avg: {{avg:.1f}}")

# Creating a dictionary
patient = {{
    "id":          "P001",
    "name":        "Chinwe Eze",
    "age":         34,
    "diagnosis":   "Type 2 Diabetes",
    "hba1c":       [7.2, 6.9, 7.5, 6.8],   # values can be lists
    "enrolled":    True
}}

# Accessing values
print(patient["name"])               # Chinwe Eze
print(patient.get("blood_group", "Not recorded"))  # safe access - no KeyError

# Modifying
patient["treatment"] = "Metformin"   # add new key
patient["age"] = 35                  # update existing key

# Checking existence
print("diagnosis" in patient)        # True
print("weight" in patient)           # False

# Iterating
for key, value in patient.items():
    print(f"  {{key:15s}}: {{value}}")

# Dictionary of dictionaries (nested)
hospital_db = {{
    "P001": {{"name": "Chinwe", "age": 34, "ward": "A"}},
    "P002": {{"name": "Emeka",  "age": 52, "ward": "B"}},
    "P003": {{"name": "Ngozi",  "age": 28, "ward": "A"}},
}}

# Access nested value
print(hospital_db["P002"]["name"])   # Emeka

# Count patients per ward
ward_counts = {{}}
for pid, data in hospital_db.items():
    ward = data["ward"]
    ward_counts[ward] = ward_counts.get(ward, 0) + 1
print(ward_counts)    # {{'A': 2, 'B': 1}}

# Sets automatically eliminate duplicates
raw_regions = ["South-West", "North-Central", "South-West",
               "South-East", "North-West", "South-West", "South-East"]

unique_regions = set(raw_regions)
print(f"Unique regions: {{len(unique_regions)}}")
print(unique_regions)    # order is not guaranteed

# Membership testing (faster than list for large datasets)
print("South-West" in unique_regions)    # True  - O(1)
print("North-East" in unique_regions)    # False

# Set operations
study_A = {{"P001", "P002", "P004", "P007", "P010"}}
study_B = {{"P002", "P005", "P007", "P011"}}

both   = study_A & study_B      # intersection: in A AND B
either = study_A | study_B      # union: in A OR B
only_A = study_A - study_B      # difference: in A but not B

print(f"In both studies: {{both}}")
print(f"In either study: {{len(either)}} participants")
print(f"Only in Study A: {{only_A}}")

# Use case: find common columns between two datasets
df1_cols = {{"id", "age", "income", "region", "outcome"}}
df2_cols = {{"id", "age", "credit_score", "region", "default"}}
shared   = df1_cols & df2_cols
print(f"Shared columns: {{shared}}")

# Syntax: [expression  for item in iterable  if condition]

numbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

# Squares of all numbers
squares = [n**2 for n in numbers]

# Even numbers only
evens = [n for n in numbers if n % 2 == 0]

# Squares of even numbers
even_squares = [n**2 for n in numbers if n % 2 == 0]
print(even_squares)   # [4, 16, 36, 64, 100]

# Data science use: normalise scores to 0-1 range
scores = [55, 72, 88, 91, 64, 77]
min_s = min(scores)
max_s = max(scores)
normalised = [(s - min_s) / (max_s - min_s) for s in scores]
print([round(v, 3) for v in normalised])

# String processing: clean a list of region names
raw = ["  Lagos ", "KANO", "abuja ", "Lagos", "kano"]
clean = [r.strip().title() for r in raw]
print(clean)   # ["Lagos", "Kano", "Abuja", "Lagos", "Kano"]

# Dictionary comprehension
words = ["data", "science", "machine", "learning"]
word_lengths = {{word: len(word) for word in words}}
print(word_lengths)  # {{"data": 4, "science": 7, ...}}

# Reading a text file
# Always use "with" - it automatically closes the file even if an error occurs
with open("data.txt", "r") as f:
    content = f.read()          # entire file as one string
    
with open("data.txt", "r") as f:
    lines = f.readlines()       # list of strings, one per line

# Writing to a file ("w" overwrites; "a" appends)
results = ["72 - Pass", "88 - Distinction", "51 - Pass", "48 - Fail"]

with open("results.txt", "w") as f:
    f.write("Exam Results\n")
    f.write("="*30 + "\n")
    for line in results:
        f.write(line + "\n")

print("File written successfully")

import csv

# Writing a CSV file
students = [
    {{"name": "Amara Okafor",  "score": 88, "grade": "Distinction"}},
    {{"name": "Emeka Nwosu",   "score": 74, "grade": "Merit"}},
    {{"name": "Ngozi Adeyemi", "score": 61, "grade": "Pass"}},
    {{"name": "Tunde Bakare",  "score": 45, "grade": "Fail"}},
]

with open("students.csv", "w", newline="") as f:
    fieldnames = ["name", "score", "grade"]
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()        # write the column header row
    writer.writerows(students)  # write all data rows

# Reading a CSV file back
with open("students.csv", "r") as f:
    reader = csv.DictReader(f)  # each row is a dictionary
    data = list(reader)

# Count grades
grade_counts = {{}}
for row in data:
    g = row["grade"]
    grade_counts[g] = grade_counts.get(g, 0) + 1
print(grade_counts)

# Average score
avg = sum(float(row["score"]) for row in data) / len(data)
print(f"Average score: {{avg:.1f}}")