micahmelling

def run_match_up_simulation(fastball_surrender_prob, curve_surrender_prob, change_surrender_prob, fastball_hit_prob,
                            curve_hit_prob, change_hit_prob, zero_zero_pitch_probs, zero_zero_hit_surrender_prob,
                            zero_zero_hit_prob, one_zero_pitch_probs, one_zero_hit_surrender_prob, one_zero_hit_prob,
                            zero_one_pitch_probs, zero_one_hit_surrender_prob, zero_one_hit_prob, one_one_pitch_probs,
                            one_one_hit_surrender_prob, one_one_hit_prob, two_zero_pitch_probs,
                            two_zero_hit_surrender_prob, two_zero_hit_prob, zero_two_pitch_probs,
                            zero_two_hit_surrender_prob, zero_two_hit_prob, one_two_pitch_probs,
                            one_two_hit_surrender_prob, one_two_hit_prob, two_one_pitch_probs,
                            two_one_hit_surrender_prob, two_one_hit_prob, three_zero_pitch_probs,
                            three_zero_hit_surrender_prob, three_zero_hi

micahmelling

def run_pitch_simulation(count, count_swing_prob, pitch_probs, count_surrender_prob, fastball_surrender_prob,
                             count_hit_prob, fastball_hit_prob, curve_surrender_prob, curve_hit_prob,
                             change_surrender_prob, change_hit_prob, df):

micahmelling

        if pitch == 'fastball':
            hit_prob = (count_surrender_prob + fastball_surrender_prob + count_hit_prob + fastball_hit_prob) / 4
            if swing == 'yes':
                outcome = np.random.choice(a=['hit', 'no_hit'], p=[hit_prob, 1 - hit_prob])
            elif swing == 'no':
                outcome = 'no_hit'
            df = df.append(pd.DataFrame({'count': count, 'pitch': 'fastball', 'swing': swing, 'result': [outcome]}))

        elif pitch == 'curve':
            hit_prob = (count_surrender_prob + curve_surrender_prob + count_hit_prob + curve_hit_prob) / 4

micahmelling

pitch = np.random.choice(a=['fastball', 'curve', 'change'], p=pitch_probs)
swing = np.random.choice(a=['yes', 'no'], p=[count_swing_prob, 1 - count_swing_prob])

micahmelling

at_bat_results = pd.DataFrame()

at_bat_results = run_pitch_simulation(count='0-0',
                                      count_swing_prob=zero_zero_swing_prob,
                                      pitch_probs=zero_zero_pitch_probs,
                                      count_surrender_prob=zero_zero_hit_surrender_prob,
                                      fastball_surrender_prob=fastball_surrender_prob,
                                      count_hit_prob=zero_zero_hit_prob,
                                      fastball_hit_prob=fastball_hit_prob,
                                      curve_surrender_prob=curve_surrender_prob,

micahmelling

last_row_df = at_bat_results.tail(1)

if last_row_df['swing'].any() == 'yes':
   end_of_at_bat = np.random.choice(a=['yes', 'no'], p=[swing_produces_out, 1 - swing_produces_out])
else:
   end_of_at_bat = 'no'

if at_bat_results['result'].any() == 'no_hit' and end_of_at_bat == 'no':
   new_count = np.random.choice(a=['0-1', '1-0'], p=[0.50, 0.50])

micahmelling

simulation_runs = 100
counter = 0
while counter < simulation_runs:
    temp_df = run_match_up_simulation(fastball_surrender_prob, curve_surrender_prob, change_surrender_prob,
                                      fastball_hit_prob, curve_hit_prob, change_hit_prob, zero_zero_pitch_probs,
                                      zero_zero_hit_surrender_prob, zero_zero_hit_prob, one_zero_pitch_probs,
                                      one_zero_hit_surrender_prob, one_zero_hit_prob, zero_one_pitch_probs,
                                      zero_one_hit_surrender_prob, zero_one_hit_prob, one_one_pitch_probs,
                                      one_one_hit_surrender_prob, one_one_hit_prob, two_zero_pitch_probs,
                                      two_zero_hit_surrender_prob, two_zero_hit_prob, zero_two_pitch_probs,

micahmelling

import pandas as pd
import subprocess

from sklearn.tree import DecisionTreeClassifier, export_graphviz


def main():
    df = pd.DataFrame({
        'location': ['MO', 'MO', 'MO', 'MO', 'KS', 'KS', 'KS', 'IL', 'IL', 'IL'],
        'age': [29, 30, 21, 40, 45, 60, 35, 24, 47, 50],

micahmelling

#!/bin/bash

# create directories
mkdir data
mkdir helpers
mkdir modeling
mkdir scratch
mkdir tests
mkdir utilities

micahmelling

import sqlite3
import pandas as pd
import numpy as np

from time import sleep
from datetime import datetime


def connect_to_sqlite(db_name):
    """