import pandas as pd

df = pd.read_csv('/home/wojciech/Pulpit/1/tit_train.csv', na_values="-1")
df.head(2)

	Unnamed: 0	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th…	female	38.0	1	0	PC 17599	71.2833	C85	C

I started with a loop connecting two functions in pairs

## ile jest zmiennych
a,b = df.shape     #<- ile mamy kolumn
b

13

for i in range(1,b):
    i = df.columns[i]
    for f in range (1,b):
        f = df.columns[f]
        print(i,f)
       

Using loops in place of gaps I insert values out of range

print('NUMBER OF EMPTY RECORDS vs. FULL RECORDS')
print('----------------------------------------')
for i in range(1,b):
    i = df.columns[i]
    r = df[i].isnull().sum()
    h = df[i].count()
   
    if r > 0:
        print(i,"--------",r,"--------",h) 

df.fillna(-777, inplace=True)

df = df.dropna(how='any')
df.isnull().sum()

Unnamed: 0     0
PassengerId    0
Survived       0
Pclass         0
Name           0
Sex            0
Age            0
SibSp          0
Parch          0
Ticket         0
Fare           0
Cabin          0
Embarked       0
dtype: int64

df.shape

(891, 13)

Encodes discrete (categorical) variables

import numpy as np

a,b = df.shape     #<- ile mamy kolumn
b


print('DISCRETE FUNCTIONS CODED')
print('------------------------')
for i in range(1,b):
    i = df.columns[i]
    f = df[i].dtypes
    if f == np.object:
        print(i,"---",f)   
    
        if f == np.object:
        
            df[i] = pd.Categorical(df[i]).codes
        
            continue
    

I run the LinearRegression () model

y = df['Survived']
X = df.drop('Survived', axis=1)

from sklearn.linear_model import LinearRegression

regr = LinearRegression() 
 

I create loops for two variables based on LinearRegression ()

c,b = df.shape     #<- ile mamy kolumn
print('b: ',b)

a = list(range(1,b))
print('a :', a)

from sklearn import metrics
b= b-2


for i in range(1,b):
    i = a[i]
    for f in range (1,b):
        f = a[f]
        
        y = df['Survived']       
        X = df.drop('Survived', axis=1)
        
        #a = X.columns[i]
        
        #b = X.columns[f]
        
        col = X.columns[[i,f]]   #<-- nazwy kolumn
        X = X[col]               #<-- FAKTYCZNE warianty zbioru X
        regr.fit(X, y)
        y_pred = regr.predict(X)
        R = regr.score(X, y)
        R2 = np.sqrt(metrics.mean_squared_error(y, y_pred))
        RR2 = R2+R
        if RR2 > 0.72:
        # print(' R2: 
            print(' RR2: 
        

I create loops for three variables based on LinearRegression ()

from sklearn import metrics

for i in range(1,b):
    i = a[i]
    for f in range (1,b):
        f = a[f]
        for g in range (1,b):
            g = a[g]
        
        
            y = df['Survived']       
            X = df.drop('Survived', axis=1)
        
            
            col = X.columns[[i,f,g]]   #<-- nazwy kolumn
            X = X[col]               #<-- FAKTYCZNE warianty zbioru X
            regr.fit(X, y)
            y_pred = regr.predict(X)
            R = regr.score(X, y)
            R2 = np.sqrt(metrics.mean_squared_error(y, y_pred))
            RR2 = R2+R
            if RR2 >= 0.757:
       
                print(' RR2: 
        

I create loops for four variables based on LinearRegression ()

from sklearn import metrics

for i in range(1,b):
    i = a[i]
    for f in range (1,b):
        f = a[f]
        for g in range (1,b):
            g = a[g]
            for r in range (1,b):
                r = a[r]
        
            y = df['Survived']       
            X = df.drop('Survived', axis=1)
        
            
            col = X.columns[[i,f,g,r]]   #<-- nazwy kolumn
            X = X[col]               #<-- FAKTYCZNE warianty zbioru X
            regr.fit(X, y)
            y_pred = regr.predict(X)
            R = regr.score(X, y)
            R2 = np.sqrt(metrics.mean_squared_error(y, y_pred))
            RR2 = R2+R
            if RR2 >= 0.761:
       
                print(' RR2: 
        

I am starting the RandomForestRegressor model

y = df['Survived']       
X = df.drop('Survived', axis=1)
print(X.shape)
print(y.shape)

from sklearn.ensemble import RandomForestRegressor

model_RFC1 = RandomForestRegressor().fit(X, y)

from sklearn import metrics

for i in range(1,b):
    i = a[i]
    for f in range (1,b):
        f = a[f]
        for g in range (1,b):
            g = a[g]
        
        
            y = df['Survived']       
            X = df.drop('Survived', axis=1)
        
            
            col = X.columns[[i,f,g]]   #<-- nazwy kolumn
            X = X[col]               #<-- FAKTYCZNE warianty zbioru X
            model_RFC1.fit(X, y)
            y_pred2 = model_RFC1.predict(X)
            R = model_RFC1.score(X, y)
            R2 = np.sqrt(metrics.mean_squared_error(y, y_pred2))
            RR2 = R2+R
            if RR2 >= 1.05:
       
                print(' RR2: 

My own tractor comes to similar conclusions as other tools in the series: Feature Selection Techniques.
Only that my tractor is probably faster in calculations …..