
# 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
import matplotlib.pyplot as plt
from prettytable import PrettyTable
plt.xkcd(scale=0,randomness=4)


# Name of sprinters
sprinters = ['Pavlos','Hargun','Joy','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):
    sprinters_dict[sprinter] = Sprinter(*characteristics[idx])


# Call time attribute
___


# Get the times for each participant and make a dictionary
race = ___
# Then sort the items of the dictionary to get the winner
# Hint: Remember to sort by the values and not the keys
winner = ___


# Again get the times for each participant and make a dictionary
race = ___
# Then sort the items of the dictionary to get the winner
winner = ___

# Execute the following code
for i in range(1,11):
    clear_output(wait=True)
    print("|START|"+"\n|START|".join(['----'*min(10,int((15*i)/race[runner]))+ '    '*(10-min(10,int((15*i)/race[runner])))+'|'+runner for runner in race.keys()]))
    sleep(0.5)
    
print(f'\nThe winner is {winner[0]} with a time of {winner[1]:.2f}s!')


# Run the simulation and append winners to the winner_list
winner_list = []
for simulation in range(5):
    race = ___
    winner = ___
    ___
    
winner_list


# Run the simulation and append winners to the winner_list
___


# Get the counts for each person winning the race
wins = Counter(___)
print(wins)


# Execute the code 
plt.bar(list(wins.keys()),list(wins.values()),alpha=0.5)
plt.xlabel('Sprinters')
plt.ylabel('Race wins',rotation=0,labelpad=30)


# Run the earlier simulation and store all 10000 times given by a participant
# race_results has a list of times as values for a given key( i.e participant)
# So for a key it has a corresponding list of times for that participant.

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


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


# loop through the keys of race_results
# calculate mean and std of each participant using np.mean() and np.std()
# Assign these stats to the key, as a list
race_stats = {}
for sprinter in race_results.keys():
    sprinter_mean = ___
    sprinter_std = ___
    race_stats[sprinter] = [___,___]


# 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 Hargun's race runs.
CI = np.percentile(___,[___,___])
print(f'The 95% confidence interval for Hargun is {round(CI[0],2),round(CI[1],2)}')


# Now lets repeat the same, 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
# Hint: You can use the .extend() method to add it to the existing list of stats
for sprinter,runs in race_results.items():
    ci = np.percentile(___)
    race_stats[___].___


# 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)


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)
plt.show()


### edTest(test_chow1) ###
# Submit an answer choice as a string below (eg. if you choose option A put 'A')

answer = '___'


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

answer = '___'


# Your code here

Title :¶

Description :¶

Data Description:¶

Instructions:¶

Hints:¶

PyDS Olymipics : 100m dash¶

Taking a look at the competitors¶

Running a race¶

Race simulation¶

Multiple simulations¶

Even more simulations¶

Why is Joy 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¶

⏸ Take a look at the histograms for each participant and comment on why do you think Joy is winning the most races?¶

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

👩🏻‍🎓 Bonus (Not graded)¶