MLWhiz

player_df = player_df.fillna(0)
results = associations(player_df,nominal_columns=catcols,return_results=True)

MLWhiz

filtered_player_df = player_df[(player_df['Club'].isin(['FC Barcelona', 'Paris Saint-Germain',
       'Manchester United', 'Manchester City', 'Chelsea', 'Real Madrid','FC Porto','FC Bayern München'])) & 
                      (player_df['Nationality'].isin(['England', 'Brazil', 'Argentina',
       'Brazil', 'Italy','Spain','Germany'])) 
                     ]
# Single line to create pairplot
g = sns.pairplot(filtered_player_df[['Value','SprintSpeed','Potential','Wage']])

MLWhiz

g = sns.pairplot(filtered_player_df[['Value','SprintSpeed','Potential','Wage','Club']],hue = 'Club')

MLWhiz

g = sns.swarmplot(y = "Club",
              x = 'Wage', 
              data = filtered_player_df,
              # Decrease the size of the points to avoid crowding 
              size = 7)
# remove the top and right line in graph
sns.despine()
g.figure.set_size_inches(14,10)
plt.show()

MLWhiz

g = sns.boxplot(y = "Club",
              x = 'Wage', 
              data = filtered_player_df, whis=np.inf)
g = sns.swarmplot(y = "Club",
              x = 'Wage', 
              data = filtered_player_df,
              # Decrease the size of the points to avoid crowding 
              size = 7,color = 'black')
# remove the top and right line in graph
sns.despine()

MLWhiz

max_wage = filtered_player_df.Wage.max()
max_wage_player = filtered_player_df[(player_df['Wage'] == max_wage)]['Name'].values[0]
g = sns.boxplot(y = "Club",
              x = 'Wage', 
              data = filtered_player_df, whis=np.inf)
g = sns.swarmplot(y = "Club",
              x = 'Wage', 
              data = filtered_player_df,
              # Decrease the size of the points to avoid crowding 
              size = 7,color='black')

MLWhiz

import random
import pandas as pd
import numpy as np
from multiprocessing import  Pool

def add_features(df):
    df['question_text'] = df['question_text'].apply(lambda x:str(x))
    df["lower_question_text"] = df["question_text"].apply(lambda x: x.lower())
    df['total_length'] = df['question_text'].apply(len)
    df['capitals'] = df['question_text'].apply(lambda comment: sum(1 for c in comment if c.isupper()))

MLWhiz

# taken from https://medium.com/@pouryaayria/k-fold-target-encoding-dfe9a594874b
from sklearn import base
from sklearn.model_selection import KFold

class KFoldTargetEncoderTrain(base.BaseEstimator,
                               base.TransformerMixin):
    def __init__(self,colnames,targetName,
                  n_fold=5, verbosity=True,
                  discardOriginal_col=False):
        self.colnames = colnames

MLWhiz

import random
# Lets define our Beta Function to generate s for any particular state. We don't care for the normalizing constant here.
def beta_s(w,a,b):
    return w**(a-1)*(1-w)**(b-1)

# This Function returns True if the coin with probability P of heads comes heads when flipped.
def random_coin(p):
    unif = random.uniform(0,1)
    if unif>=p:
        return False

MLWhiz

import numpy as np
import pylab as pl
import scipy.special as ss
%matplotlib inline
pl.rcParams['figure.figsize'] = (17.0, 4.0)

# Actual Beta PDF.
def beta(a, b, i):
    e1 = ss.gamma(a + b)
    e2 = ss.gamma(a)