lmeulen

winners = stats.get_winners()
wins = winners[['driverId', 'driver', 'race']].groupby(['driverId', 'driver']). \
       count().reset_index()

stats.horizontal_barplot(df=wins, rowcount=10, sort_value='race',
                         sort_ascending=False, invert_yaxis=True,
                         xcolumn='driver', ycolumn='race',
                         title='Drivers with most wins', 
                         xlabel='wins', ylabel='')

lmeulen

class F1Stats:
  
    ...
    
    def get_winners(self):
        winners = self.get_race_results()
        return winners[winners.position == 1].copy()

    def get_quali_results(self):
        qualiresults = \

lmeulen

def horizontal_driver_lines_plot(df, xcolumn, ycolumn, invert_yaxis=False, 
                                 title = '', xlabel='', ylabel='', 
                                 ymin=None, ymax=None):
    fig, ax = plt.subplots(figsize=(15,10))
    drivers = df['code'].unique()
    for driver in drivers:
        df[df.code == driver].plot(xcolumn, ycolumn, ax=ax, label=driver, 
                                   color=stats.get_driver_color(driver))
    ax.get_legend().remove()
    if invert_yaxis: ax.invert_yaxis()

lmeulen

class F1Stats

    ...
    
    def get_wdc_standing(self, year=None):
        standings = \
           self.dfs["driver_standings"]. \
            merge(self.dfs["races"][['raceId', 'year', 'round', 'name']].rename(columns={'name':'race'}), 
                  on='raceId') .\
            merge(self.dfs["drivers"][['driverId', 'name', 'code']])

lmeulen

def horizontal_barplot(df, rowcount, sort_value, sort_ascending, 
                       xcolumn, ycolumn, title='', 
                       xlabel='', ylabel='', invert_yaxis=True):

    fig, ax = plt.subplots(figsize=(15,8))
    plot_data = df.sort_values(sort_value, ascending=sort_ascending)[:rowcount]

    rects = ax.barh(plot_data[xcolumn], plot_data[ycolumn])
    for rect in rects:
        yloc = rect.get_y() + rect.get_height() / 2    # Center the text vertically in the bar

lmeulen

class F1Stats

    ...

    def get_race_results(self):
        raceresults = pd.merge(self.dfs['results'][['resultId', 'raceId', 'driverId', 'constructorId', 
                                                    'grid','position', 'positionText', 'points']], 
                               self.dfs['races'][['raceId', 'year', 'round', 'name', 'date']]. \
                                    rename(columns={'name': 'race'}))
        raceresults = pd.merge(raceresults,

lmeulen

    def cleanup_data(self):
        # Races
        self.__column_strip_string("races", ["name"])
        self.__column_to_datetime("races", "date", "time")
        self.__column_to_datetime("races", "fp1_date", "fp1_time", "fp1")
        self.__column_to_datetime("races", "fp2_date", "fp2_time", "fp2")
        self.__column_to_datetime("races", "fp3_date", "fp3_time", "fp3")
        self.__column_to_datetime("races", "quali_date", "quali_time", "quali")
        self.__column_to_datetime("races", "sprint_date", "sprint_time", "sprint")
        self.__drop_columns("races", ["url"])

lmeulen

    def __column_strip_string(self, dfname, columnnames):
        for c in columnnames:
            self.dfs[dfname][c] = self.dfs[dfname][c].str.strip()

    def __column_to_int(self, dfname, columnnames, default=0):
        for c in columnnames:
            self.dfs[dfname][c] = self.dfs[dfname][c].replace('',default).astype(int)

    def __column_to_float(self, dfname, columnnames, default=0):
        for c in columnnames:

lmeulen

import requests
import os
import pickle
import pandas as pd
from zipfile import ZipFile

class F1Stats:
    
    zipfile=None
    cachefile=None

lmeulen

from sklearn.neural_network import MLPRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Split the dataset in train and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# Scale inputs
sc_X = StandardScaler()
X_trainscaled=sc_X.fit_transform(X_train)