Module 8 - Tutorial - Logistic Regression

import pandas as pd

import numpy as np

import sklearn

import matplotlib.pyplot as plt

import seaborn as sns

%matplotlib inline

from sklearn.linear_model import LogisticRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import classification_report

from sklearn.metrics import confusion_matrix

location = titanic.xls

df = pd.read_excel(location)

df.head()

#bar chart of survival status count

sns.countplot(x='survived', data=df)

#survival status by sex

sns.barplot('sex', 'survived', data=df)

#survival rate by passenger class

sns.barplot('pclass', 'survived', data=df)

#plot age by survival status

plt.figure(figsize=(10,6))

ax = sns.kdeplot(df['age'][df['survived'] == 1], #passengers that survived

                 color="darkturquoise",

                 shade=True)

sns.kdeplot(df['age'][df['survived'] == 0], #passengers that did not survive

            color="lightcoral",

            shade=True)

plt.legend (['Survived', 'Died'])

plt.title("Density Plot of Age for Survived vs Deceased Population")

ax.set(xlabel='Age')

#plt.show()

#find columns that have missing values

df.isnull().sum()

#rows where the age is missing

missing_age = df.loc[df['age'].isnull()]

missing_age.head()

#get index numbers of missing rows - we'll use this later

mals = list(missing_age.index)

#table of avg age of passenger by survival status, sex, and passenger class

df.groupby(['survived', 'sex', 'pclass'])['age'].mean()

#fill missing values for age based on survival status, sex, and passenger class

df['age'].fillna(df.groupby(['survived', 'sex', 'pclass'])['age'].transform('mean'), inplace=True)

#verify filled missing values 

df.iloc[mals].head()

#verify there are no more missing age values

df.isnull().sum()

#missing values for 'embarked'

embark = df.loc[df['embarked'].isnull()]

embark

#save index for missing values to verify later

embarkls = list(embark.index)

#only 2 missing values so we'll fill with most common embarkation point

df['embarked'].value_counts()

#fill missing values

df['embarked'].fillna('S', inplace=True)

#check that they're filled

df.iloc[embarkls]

df.isnull().sum()

modeldf = df.drop(['name','ticket','fare', 'cabin', 'boat', 'body', 'home.dest'], axis=1)

#columns left in our dataframe

modeldf.columns

#dummy variables for passenger class embarkation port

#get_dummies will auto-drop columns that dummies were created from

modeldf = pd.get_dummies(data=modeldf, columns=['pclass','embarked'])

modeldf.head()

#change sex values to binary

#female=0, male=1

modeldf['sex'] = modeldf['sex'].map({'female':0, 'male':1})

modeldf.head()

#create new column based on number of family members

#drop sibsp and parch columns

modeldf['family_num'] = modeldf['sibsp'] + modeldf['parch']

modeldf.drop(['sibsp', 'parch'], axis=1, inplace=True)

modeldf.head()

modeldf['TravelAlone']=np.where((modeldf['family_num'] > 0), 0, 1)

modeldf.head()

#extract target variable

#make copy of 'survived' column

y = modeldf['survived']

#copy of modeldf without 'survived' column

X = modeldf.drop(['survived'], axis=1)

#80% for training data, 20% for test data

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=15)

#build logistic regression model

LogReg = LogisticRegression()

LogReg.fit(X_train, y_train)

#accuracy score of model using training data

LogReg.score(X_train, y_train)

#generate prediction values

y_pred = LogReg.predict(X_test)

#Confusion matrix shows which values model predicted correctly vs incorrectly

cm = pd.DataFrame(

    confusion_matrix(y_test, y_pred),

    columns=['Predicted Not Survival', 'Predicted Survival'],

    index=['True Not Survival', 'True Survival']

)

cm

#accuracy score of model on test data

LogReg.score(X_test, y_test)

#from precision column, model is better at predicting passengers that do not survive

print(classification_report(y_test, y_pred))