
# Importing libraries
import numpy as np
from time import sleep
import os
from IPython.display import clear_output
from collections import Counter
from helper import Sprinter
from helper import run_sim
import matplotlib.pyplot as plt
from prettytable import PrettyTable
plt.xkcd(scale=0,randomness=4)

<matplotlib.pyplot._xkcd at 0x7f8dbe7bdfd0>


# Name of sprinters
sprinters = ['Pavlos','Tale','Varshini','Hayden']

# Defining charactersistics, ('Base pace','performance variance')
characteristics = [(13,0.25),(12.5,0.5),(12.25,1),(14.5,1)]
sprinters_dict = {}

for idx,sprinter in enumerate(sprinters):

    # Take note of the * before characteristics
    sprinters_dict[sprinter] = Sprinter(*characteristics[idx])


# Call time attribute
___


### edTest(test_chow0) ###
# Submit an answer choice as a string below (eg. if you choose option A put 'A')
answer = '___'


### edTest(test_race) ###
# Get the times for each participant and make a dictionary
race = ___

# Sort the items of the dictionary to get the winner
# Hint: Remember to sort by the values and not the keys
winner = ___


# Get the times for each participant and make a dictionary
race = {sprinter:dash.time for sprinter,dash in sprinters_dict.items()}

# Sort the items of the dictionary to get the winner
winner = sorted(race.items(),key=lambda x:x[1])[0]

# Uncomment and execute the following code
# run_sim(race,winner)


# Run the simulation and append winners to the winner_list
# Create an empty list
winner_list = []

# Run a simulation for 5 loops
for simulation in range(5):

    # Create a race dictionary
    race = {k:v.time for k,v in sprinters_dict.items()}

    # Sort the items
    winner = sorted(race.items(),key=lambda x:x[1])[0]

    # Append the name of the winner to winners_list
    winner_list.append(winner)
    
# Take a look at the winners list
winner_list


# Run the simulation and append winners to the winner_list
# Create an empty list
winner_list = []

# Run a simulation for 10000 loops
for simulation in range(10000):

    # Create race dictionary
    race = {k:v.time for k,v in sprinters_dict.items()}

    # Sort the items
    winner = sorted(race.items(),key=lambda x:x[1])[0]

    # Append the name of the winner to winners_list
    winner_list.append(winner[0])
    
# Display first 5 entries from winner_list
winner_list___


### edTest(test_wins) ###
# Get the counts for each person winning the race
# Hint: Use counter, look at the hints 
wins = Counter(winner_list)

# Print wins to see the output of the simulation
print(___)


# Helper code to plot the wins of each sprinter
plt.bar(list(wins.keys()),list(wins.values()),alpha=0.5)
plt.xlabel('Sprinters')
plt.ylabel('Race wins',rotation=0,labelpad=30)
plt.show();


# Run the earlier simulation loop for 10000 times
# Loop over the sprinters_dict items and for each participant
# Call time and append to the corresponding list in race_results

race_results= {k:[] for k in sprinters_dict.keys()}
for simulation in range(10000):
    for sprinter,dash in sprinters_dict.items():

        # For a given participant call the .time attribute
        sprint_timing = dash.time
        race_results[sprinter].append(sprint_timing)


# Using the race_results dictionary, find the mean
# and std for 'Pavlos'
pavlos_mean = ___
pavlos_std = ___
print(f'The average pace of Pavlos is {pavlos_mean:.2f} and the sample std is {pavlos_std:2f}')


# Calculate mean and std of each participant

# Initialize an empty dictionary
race_stats = {}

# Loop over race_results.keys()
for sprinter in race_results.keys():
    sprinter_mean = np.mean(race_results[sprinter])
    sprinter_std = np.std(race_results[sprinter])

    # Store it as a list [mean,std] corresponding to each 
    # participant key in race_stats
    race_stats[sprinter] = [sprinter_mean,sprinter_std]


# Use the helper code below to print your findings
pt = PrettyTable()

pt.field_names = ["Sprinter", "Sample mean", "Sample std"]

for sprinter,stats in race_stats.items():
    pt.add_row([sprinter, round(stats[0],3),round(stats[1],3)])

print(pt)


#By using the race_results dictionary defined above,
# Find the 2.5 and 97.5 percentile of Tale's race runs.
# Hint : Use race_results['Tale's']
CI = np.percentile(___,[___,___])
print(f'The 95% confidence interval for Tale is {round(CI[0],2),round(CI[1],2)}')


# Repeat the same as above, but for every sprinter
# run through the race_results dictionary for each sprinter
# find the confidence interval, and add it to the race_stats dictionary 
# defined above

for sprinter,runs in race_results.items():
    ci = np.percentile(runs,[2.5,97.5])

    # Hint: You can use the .extend() method to add it to the 
    # existing list of stats
    race_stats[sprinter].extend(ci)


# Use the helper code below to print your findings
pt = PrettyTable()

pt.field_names = ["Sprinter", "Sample mean", "Sample std","95% CI"]

for sprinter,stats in race_stats.items():
    mean = round(stats[0],3)
    std = round(stats[1],3)
    confidence_interval = (round(stats[2],3),round(stats[3],3))
    pt.add_row([sprinter, mean,std,confidence_interval])

print(pt)


# Helper code to plot the distribution of times
fig = plt.gcf()
fig.set_size_inches(10,6)
bins = np.linspace(10, 17, 50)

for sprinter,runs in race_results.items():
    height, bins, patches = plt.hist(runs, bins, alpha=0.5, \
                            label=sprinter,density=True,edgecolor='k')
    plt.fill_betweenx([0, height.max()], race_stats[sprinter][2], race_stats[sprinter][3], alpha=0.2)
plt.legend(loc='upper left',fontsize=16)
plt.xlabel('Seconds')
plt.ylabel('Frequency',rotation=0,labelpad=25)
ax = plt.gca()
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.set_title('Time distribution for sprinters')
plt.show()


### edTest(test_chow1) ###
# Write your answer as a string below
answer = '___'


### edTest(test_chow2) ###
# Submit an answer choice as a string below (eg. if you choose option A put 'A')
answer = '___'


# Before you click mark, please comment out the run_sim function above


# Your code here

Title :¶

Description :¶

Data Description:¶

Instructions:¶

Hints:¶

CS109A Olympics : 100m dash¶

Taking a look at the competitors¶

Running a race¶

⏸ Pause & Think¶

Race simulation¶

Multiple simulations¶

Even more simulations¶

Why is Varshini winning so much ?¶

Sample mean $\bar{x}$ sample standard deviation $s$¶

Sample mean $\bar{x}$ sample standard deviation $s$ for all sprinters¶

Confidence Interval¶

Confidence intervals for all sprinters.¶

Histogram plot for each sprinter¶

⏸ Pause & Think¶

⏸ What one parameter should Tale change in order to win more races?¶

👩🏻‍🎓 Bonus (Not graded)¶