# Let us start by making a simple list of numbers to represent test scores.
scores = [90, 85, 78, 82, 95, 88, 76, 91, 87, 85]
print('Test scores:', scores)

# To understand how the scores are spread out, let us check their minimum and maximum values.
minimum = min(scores)
maximum = max(scores)
print('Lowest score:', minimum)
print('Highest score:', maximum)

# Let us calculate the average score, also called the mean.
average = sum(scores) / len(scores)
print('Average score:', average)

# Median helps us know the middle value in our sorted data.
sorted_scores = sorted(scores)
n = len(sorted_scores)
if n % 2 == 1:
    median = sorted_scores[n//2]
else:
    median = (sorted_scores[n//2 - 1] + sorted_scores[n//2]) / 2
print('Median score:', median)

# Let us check how far scores are from the average using standard deviation.
import math
mean = average
variance = sum((x - mean)**2 for x in scores) / len(scores)
std_dev = math.sqrt(variance)
print('Standard deviation:', std_dev)

# Print the sorted scores to see the shape of our data.
print('Sorted scores:', sorted_scores)

# Let us find the most common score using a frequency count.
from collections import Counter
counts = Counter(scores)
most_common = counts.most_common(1)[0]
print('Most common score:', most_common[0], 'appears', most_common[1], 'times')

# Let us make two lists: hours studied and scores received.
hours_studied = [5, 4, 3, 2, 6, 4, 1, 5, 3, 2]
print('Hours studied:', hours_studied)
print('Test scores:', scores)

# Let us pair up hours and scores to look for patterns.
paired = list(zip(hours_studied, scores))
print('Hours and scores:', paired)

# We can measure relationship strength using correlation.
def mean(lst):
    return sum(lst) / len(lst)

def correlation(x, y):
    avg_x = mean(x)
    avg_y = mean(y)
    num = sum((xi - avg_x) * (yi - avg_y) for xi, yi in zip(x, y))
    den_x = math.sqrt(sum((xi - avg_x) ** 2 for xi in x))
    den_y = math.sqrt(sum((yi - avg_y) ** 2 for yi in y))
    return num / (den_x * den_y)

corr = correlation(hours_studied, scores)
print('Correlation between hours studied and scores:', corr)

# Safe data access: Let us try reading a value and handle possible errors.
try:
    idx = int(input('Enter a student index (0-9): '))
    score = scores[idx]
    print('Student', idx, 'score:', score)
except (ValueError, IndexError):
    print('Please enter a valid index between 0 and 9.')
    

# Let us update a score to see how data changes.
print('Original scores:', scores)
scores[0] = 99
print('Updated scores:', scores)

# Remove a scorelet us see what happens to the distribution.
removed = scores.pop()
print('Removed last score:', removed)
print('Scores now:', scores)

# Quick look at built-in stats: Use statistics.mean for easy averages.
import statistics
avg2 = statistics.mean(scores)
print('Easy mean:', avg2)

# Let us loop through all scores: What if you want to know which are above 90?
high_scores = []
for score in scores:
    if score > 90:
        high_scores.append(score)
print('High scores over 90:', high_scores)

# List comprehensions give us a shorter way to filter data.
eighty_and_up = [s for s in scores if s >= 80]
print('Scores 80 or higher:', eighty_and_up)

# Let us sort the paired hours and scores by hours studied.
sorted_pairs = sorted(zip(hours_studied, scores), key=lambda x: x[0])
print('Sorted by hours studied:', sorted_pairs)

# Now, let us look at a small real-world-like set: survey ages and satisfaction.
ages = [21, 34, 19, 45, 28, 30, 40, 23, 25, 37]
satisfaction = [6, 8, 5, 7, 9, 6, 7, 8, 5, 9]
print('Ages:', ages)
print('Satisfaction (1-10):', satisfaction)

# Analyze the relationship between age and satisfaction.
corr_age_sat = correlation(ages, satisfaction)
print('Correlation between age and satisfaction:', corr_age_sat)

# Mini-project: Let us make a function that shows full summary statistics.
def summarize(data):
    print('Min:', min(data))
    print('Max:', max(data))
    print('Mean:', statistics.mean(data))
    print('Median:', statistics.median(data))
    print('Standard deviation:', statistics.stdev(data))
    counts = Counter(data)
    mode_val = counts.most_common(1)[0][0]
    print('Mode:', mode_val)

print('Summary for ages:')
summarize(ages)
print()
print('Summary for satisfaction:')
summarize(satisfaction)

# Mini-project, Part 2: Using user input to analyze your own data.
raw = input('Enter a list of numbers, separated by spaces: ')
user_data = [float(num) for num in raw.strip().split()]
print('Your data:', user_data)
summarize(user_data)

# Optimization tip: Use NumPy for even faster math on big lists.
import numpy as np
biglist = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
print('Mean:', biglist.mean())
print('Standard deviation:', biglist.std())

# Troubleshooting: Catching division by zero and empty data errors.
try:
    empty_list = []
    avg_empty = sum(empty_list) / len(empty_list)
except ZeroDivisionError:
    print('You cannot divide by zero. The list is empty.')
    

# Extra trick: Remove outliers by filtering numbers far from the mean.
mean_val = statistics.mean(scores)
std_val = statistics.stdev(scores)
filtered = [x for x in scores if abs(x - mean_val) <= 2 * std_val]
print('Scores with outliers removed:', filtered)

# Challenge: Write your own function to get the range (max minus min) of a list.
def data_range(data):
    return max(data) - min(data)

print('Range for satisfaction:', data_range(satisfaction))