#!/usr/bin/env python
# coding: utf-8

# Repeating the calculations explained [here](https://www.baseball-reference.com/about/parkadjust.shtml) in Python using `pybaseball`.

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


import numpy as np
import pandas as pd
import pybaseball


# In[3]:


# the test season from Baseball Reference/Total Baseball
SEASON = 1982
TEAM = "ATL"

# the 1982 Phillies
#SEASON = 1982
#TEAM = "PHI"

# the 2018 Phillies
#SEASON = 2018
#TEAM = "PHI"

DATA_PATH = f'./data/{TEAM}_{SEASON}.csv'

VERIFY = (SEASON == 1982) and (TEAM == "ATL")


# In[4]:


# don't download the Lahman database every time the notebook is rerun (if possible)
# see https://github.com/jldbc/pybaseball/issues/29

try:
    df = pd.read_csv(DATA_PATH)
except FileNotFoundError:
    df = pybaseball.schedule_and_record(season=SEASON, team=TEAM)
    df.to_csv(DATA_PATH, index=False)
    
df = df.rename(columns=str.lower)


# In[5]:


df.head()


# In[6]:


df['home_away'].value_counts()


# In[7]:


df['w/l'].value_counts()


# In[8]:


df['is_home'] = df['home_away'] == "Home"
df['is_win'] = df['w/l'].str.startswith("W")


# In[9]:


home_away_df = (df.groupby('is_home')
                  ['is_win', 'r', 'ra']
                  .sum()
                  .rename(columns={'is_win': 'wins'}))
home_away_df['rtot'] = home_away_df[['r', 'ra']].sum(axis=1)
home_away_df['gp'] = df['is_home'].value_counts()


# In[10]:


home_away_df


# In[11]:


home_away_pct = home_away_df['wins'] / home_away_df['gp']


# In[12]:


home_away_pct


# In[13]:


IPC = (18.5 - home_away_pct[True]) / (18.5 - (1 - home_away_pct[False]))


# In[14]:


def verify_agreement_with_total_baseball(val, true_val, name, atol=1e-3):
    assert np.allclose(val, true_val, atol=atol)
    print(f"{name} agrees with Total Baseball")


# In[15]:


if VERIFY:
    verify_agreement_with_total_baseball(IPC, 0.995, "IPC")


# In[16]:


rpg = home_away_df['rtot'] / home_away_df['gp']


# In[17]:


rpg


# In[18]:


RFT = (rpg[True] / rpg[False]) / IPC


# In[19]:


if VERIFY:
    verify_agreement_with_total_baseball(RFT, 1.170, "RFT")


# In[20]:


NT = df['opp'].nunique() + 1


# In[21]:


OPC = NT / (NT - 1 + RFT)


# In[22]:


if VERIFY:
    verify_agreement_with_total_baseball(OPC, 0.986, "OPC")


# In[23]:


SF = RFT * OPC


# In[24]:


if VERIFY:
    verify_agreement_with_total_baseball(SF, 1.154, "SF")


# In[25]:


SF1 = 1 - (SF - 1) / (NT - 1)


# In[26]:


if VERIFY:
    verify_agreement_with_total_baseball(SF1, 0.986, "SF1")


# In[27]:


home_away_df.head()


# In[28]:


RAL = 7947 / 972


# In[29]:


RAT, RHT = home_away_df['r']
OAT, OHT = home_away_df['ra']


# In[30]:


def iterate_team_ratings(TPR, RAL, NT, home_away_df):
    assert home_away_df.index.is_monotonic_increasing

    RAT, RHT = home_away_df['r'] / home_away_df['gp']
    OAT, OHT = home_away_df['ra'] / home_away_df['gp']

    TBR = (RAT / SF1 + RHT / SF) * (1 + (TPR - 1) / (NT - 1)) / RAL
    TPR_ = (OAT / SF1 + OHT / SF) * (1 + (TBR - 1) / (NT - 1)) / RAL
    
    return TBR, TPR_

def calculate_team_ratings(RAL, NT, home_away_df, TPR=1, iter=4):
    for _ in range(iter):
        TBR, TPR = iterate_team_ratings(TPR, RAL, NT, home_away_df)
        
    return TBR, TPR


# In[31]:


TBR_1iter, TPR_1iter = calculate_team_ratings(RAL, NT, home_away_df, iter=1)


# In[32]:


if VERIFY:
    verify_agreement_with_total_baseball(TBR_1iter, 1.044, "TBR", atol=1e-2)
    verify_agreement_with_total_baseball(TPR_1iter, 0.993, "TPR", atol=1e-2)


# In[33]:


TBR, TPR = calculate_team_ratings(RAL, NT, home_away_df)


# In[34]:


BPF = (SF + SF1) / (2 * (1 + (TPR - 1) / (NT - 1)))
PPF = (SF + SF1) / (2 * (1 + (TBR - 1) / (NT - 1)))


# In[35]:


if VERIFY:
    verify_agreement_with_total_baseball(BPF, 1.07, "BPF")