Logistic Regression Question

model_formula = sm.Logit.from_formula("Survived ~ Age + Parch + Fare + Pclass_1 + Pclass_2 + Pclass_3", df)

import pandas as pd
import numpy as np

#1. Read Data
df = pd.read_csv('C:/Users/minki/Downloads/Sample_data.csv', header =0)

df['Sex'] = df['Sex'].astype('category')
df['Pclass'] = df['Pclass'].astype('category') 
df[ 'Embarked'] = df['Embarked'].astype('category')
df = pd.get_dummies((df))

#2 data scaling
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler ()
df_scaled = scaler.fit_transform(df)

#3 data splitting
from sklearn.model_selection import train_test_split
Y = df['Survived']
X = df.iloc[:, 1:12] ##important to check the index
print(X)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0)

#4 Logistic regression
import statsmodels.api as sm
model_formula = sm. Logit.from_formula ("Survived Age + Parch + Fare + Pclass_1+ Pclass_2+ Pclass_3", df)
result_model = model_formula.fit() ##Build your log reg.
print (result_model.summary()) ## Chcek the reg result

print (np.exp(result_model.params)) ## calculate odds ratio of each year
Y_pred = result_model.predict(X_test) ## using test dataset, we will predict the value of :"survived"
Y_pred = list(map (round, Y_pred))
print(Y_pred)
print("----")
print(list(Y_test))

from sklearn import metrics
metrics.confusion_matrix (Y_test, Y_pred)
accuracy = metrics.accuracy_score (Y_test, Y_pred)
recall = metrics.recall_score (Y_test, Y_pred)
f1 = metrics.f1_score (Y_test, Y_pred)
print("Accuracy:", accuracy, ", F1-score:", f1, "Recall score:", recall)