From a05a072dbfb444aeabd2821f4f1420272ddc676b Mon Sep 17 00:00:00 2001
From: jfvillablanca <31008330+jfvillablanca@users.noreply.github.com>
Date: Tue, 7 Nov 2023 12:06:00 +0800
Subject: [PATCH] sol: lab6/world-cup

---
 lab6/world-cup/README.md     |  1 +
 lab6/world-cup/answers.txt   | 19 ++++++++++
 lab6/world-cup/tournament.py | 70 ++++++++++++++++++++++++++++++++++++
 3 files changed, 90 insertions(+)
 create mode 100644 lab6/world-cup/README.md
 create mode 100644 lab6/world-cup/answers.txt
 create mode 100644 lab6/world-cup/tournament.py

diff --git a/lab6/world-cup/README.md b/lab6/world-cup/README.md
new file mode 100644
index 0000000..0b75f6d
--- /dev/null
+++ b/lab6/world-cup/README.md
@@ -0,0 +1 @@
+https://cs50.harvard.edu/x/2023/labs/6/
diff --git a/lab6/world-cup/answers.txt b/lab6/world-cup/answers.txt
new file mode 100644
index 0000000..d3eede5
--- /dev/null
+++ b/lab6/world-cup/answers.txt
@@ -0,0 +1,19 @@
+Times:
+
+10 simulations: 0m0.027s
+100 simulations: 0m0.028s
+1000 simulations: 0m0.035s
+10000 simulations: 0m0.156s
+100000 simulations: 0m0.768s
+1000000 simulations: 0m6.765s
+
+Questions:
+
+Which predictions, if any, proved incorrect as you increased the number of simulations?:
+
+With a small number of simulations, the probability of a country winning is not as correlated with the rating provided.
+
+Suppose you're charged a fee for each second of compute time your program uses.
+After how many simulations would you call the predictions "good enough"?:
+
+I think, at around 10000 simulations, the rankings and winning percentages seem to have stabilized to based on historical data. It's fast enough that it runs in less than a second.
diff --git a/lab6/world-cup/tournament.py b/lab6/world-cup/tournament.py
new file mode 100644
index 0000000..e7a5927
--- /dev/null
+++ b/lab6/world-cup/tournament.py
@@ -0,0 +1,70 @@
+# Simulate a sports tournament
+
+import csv
+import sys
+import random
+
+# Number of simluations to run
+N = 1000
+
+
+def main():
+    # Ensure correct usage
+    if len(sys.argv) != 2:
+        sys.exit("Usage: python tournament.py FILENAME")
+
+    teams = []
+    # TODO: Read teams into memory from file
+    with open(sys.argv[1]) as file:
+        reader = csv.DictReader(file)
+        for team in reader:
+            team["rating"] = int(team["rating"])
+            teams.append(team)
+
+    counts = {}
+    # TODO: Simulate N tournaments and keep track of win counts
+    for i in range(N):
+        winner = simulate_tournament(teams)
+        if winner in counts:
+            counts[winner] += 1
+        else:
+            counts[winner] = 1
+
+    # Print each team's chances of winning, according to simulation
+    # for team in sorted(counts, key=lambda team: counts[team], reverse=True):
+    #     print(f"{team}: {counts[team] * 100 / N:.1f}% chance of winning")
+
+
+def simulate_game(team1, team2):
+    """Simulate a game. Return True if team1 wins, False otherwise."""
+    rating1 = team1["rating"]
+    rating2 = team2["rating"]
+    probability = 1 / (1 + 10 ** ((rating2 - rating1) / 600))
+    return random.random() < probability
+
+
+def simulate_round(teams):
+    """Simulate a round. Return a list of winning teams."""
+    winners = []
+
+    # Simulate games for all pairs of teams
+    for i in range(0, len(teams), 2):
+        if simulate_game(teams[i], teams[i + 1]):
+            winners.append(teams[i])
+        else:
+            winners.append(teams[i + 1])
+
+    return winners
+
+
+def simulate_tournament(teams):
+    """Simulate a tournament. Return name of winning team."""
+    # TODO
+    while len(teams) > 1:
+        teams = simulate_round(teams)
+
+    return teams[0]["team"]
+
+
+if __name__ == "__main__":
+    main()