TDA/lections/notebooks/lec6_titanic_classification.ipynb

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns


from sklearn import metrics
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import cross_val_score, train_test_split, GridSearchCV, StratifiedKFold

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier

from sklearn.manifold import TSNE
from sklearn.manifold import MDS


from sklearn import preprocessing

df = pd.read_csv('titanic.csv')

Знакомство с датасетом

df

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
...	...	...	...	...	...	...	...	...	...	...	...	...
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NaN	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NaN	Q

891 rows × 12 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  891 non-null    int64  
 1   Survived     891 non-null    int64  
 2   Pclass       891 non-null    int64  
 3   Name         891 non-null    object 
 4   Sex          891 non-null    object 
 5   Age          714 non-null    float64
 6   SibSp        891 non-null    int64  
 7   Parch        891 non-null    int64  
 8   Ticket       891 non-null    object 
 9   Fare         891 non-null    float64
 10  Cabin        204 non-null    object 
 11  Embarked     889 non-null    object 
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB

df.describe()

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

Предварительная обработка

# Удаляем ненужные столбцы
df = df.drop(['PassengerId', 'Ticket', 'Cabin', 'Name'], axis=1)

# Кодируем поле Пол
df.loc[df['Sex'] == 'male', 'Sex'] = 1
df.loc[df['Sex'] == 'female', 'Sex'] = 0
df.Sex = df.Sex.astype(bool)

# Кодируем поле Embarked
df.Embarked.fillna(df.Embarked.mode()[0],inplace=True)

le = preprocessing.LabelEncoder()
le.fit(df['Embarked'])
df['Embarked'] = le.transform(df['Embarked'])
df

	Survived	Pclass	Sex	Age	SibSp	Parch	Fare	Embarked
0	0	3	True	22.0	1	0	7.2500	2
1	1	1	False	38.0	1	0	71.2833	0
2	1	3	False	26.0	0	0	7.9250	2
3	1	1	False	35.0	1	0	53.1000	2
4	0	3	True	35.0	0	0	8.0500	2
...	...	...	...	...	...	...	...	...
886	0	2	True	27.0	0	0	13.0000	2
887	1	1	False	19.0	0	0	30.0000	2
888	0	3	False	NaN	1	2	23.4500	2
889	1	1	True	26.0	0	0	30.0000	0
890	0	3	True	32.0	0	0	7.7500	1

891 rows × 8 columns

# Заполняем возраст медианой
df.Age.fillna(df.Age.median(), inplace = True)

df.info()

 df['Survived'].value_counts()

Визуализация датасета

tsne = TSNE(n_components=2, 
             init="pca", 
             random_state=0,
             perplexity=50,
             n_iter = 1000,
             metric = 'cosine')

Y = tsne.fit_transform(df.iloc[:,1:])

plt.scatter(Y[:,0], Y[:,1], c = df.iloc[:,0])

# Multidimentional scaling
mds = MDS(n_components=2, 
             random_state=0)

Y_MDS = mds.fit_transform(df.iloc[:,1:])

plt.scatter(Y_MDS[:,0], Y_MDS[:,1], c = df.iloc[:,0])

Графики по столбцам

sns.countplot(x = df.Survived)

sns.countplot(x = df.Pclass, hue = df.Survived)

sns.set(rc={'figure.figsize':(10,5)})
sns.histplot(x = df.loc[df.Fare < 200].Fare, hue  = df.Survived, kde=True)

sns.set(rc={'figure.figsize':(10,5)})
sns.histplot(x = df.Age, hue  = df.Survived, kde=True )

sns.countplot(x = df.Sex, hue = df.Survived)

sns.set(rc={'figure.figsize':(10,5)})
sns.histplot(x = df.SibSp, hue  = df.Survived, kde=True )

Корреляционная матрица

sns.heatmap(df.corr(numeric_only = True), annot = True,  vmin=-1, vmax=1, cmap = 'bwr')

Классификация

X_train, X_test, y_train, y_test = train_test_split(df.iloc[:,1:], df.iloc[:,0], test_size=0.33, random_state=42) 

RF = RandomForestClassifier(random_state=42)
RF.fit(X_train, y_train)
rf_prediction = RF.predict(X_test)

print('Conf matrix')
print(metrics.confusion_matrix(rf_prediction, y_test))
print('Classification report')
print(metrics.classification_report(rf_prediction, y_test))

# Вероятности каждого класса
rf_prediction_proba = RF.predict_proba(X_test)
rf_prediction_proba

rf_prediction

Важность признаков

fi = pd.DataFrame(RF.feature_importances_, RF.feature_names_in_)
fi

 sns.barplot(fi.T)

X_train_saf = X_train[['Sex', 'Age', 'Fare']]
X_test_saf = X_test[['Sex', 'Age', 'Fare']]
RF_saf = RandomForestClassifier(random_state=42)
RF_saf.fit(X_train_saf, y_train)
rf_saf_prediction =RF_saf.predict(X_test_saf )

print('Conf matrix')
metrics.confusion_matrix(rf_saf_prediction, y_test)
print('Classification report')
print(metrics.classification_report(rf_saf_prediction, y_test))

XGBoost

from xgboost import XGBClassifier

XGB = XGBClassifier(random_state=42)
XGB.fit(X_train, y_train)
xgb_prediction =XGB.predict(X_test )
print('Conf matrix')
print(metrics.confusion_matrix(xgb_prediction, y_test))
print('Classification report')
print(metrics.classification_report(xgb_prediction, y_test))

XGB_saf = XGBClassifier(random_state=42)
XGB_saf.fit(X_train_saf, y_train)
xgb_saf_prediction =XGB_saf.predict(X_test_saf)
print('Conf matrix')
print(metrics.confusion_matrix(xgb_saf_prediction, y_test))
print('Classification report')
print(metrics.classification_report(xgb_saf_prediction, y_test))

sns.heatmap(metrics.confusion_matrix(xgb_saf_prediction, y_test), annot = True, cmap = 'RdYlGn')

Попробуем настроить параметры для RF

#X_train_sef = X_train[['Sex', 'Age', 'Fare']]
#X_test_sef = X_test[['Sex', 'Age', 'Fare']]

params = {
    'n_estimators': [1, 10, 50, 100],
    'max_depth': [1, 5, 10],
    'criterion':['gini', 'entropy']
}


RF_saf_gs = RandomForestClassifier(random_state=42)

gs = GridSearchCV(param_grid=params, estimator=RF_saf_gs)
gs.fit(X_train_saf, y_train)
rf_saf_gs_prediction=gs.predict(X_test_saf )

gs.best_params_

print('Conf matrix')
print(metrics.confusion_matrix(rf_saf_gs_prediction, y_test))
print('Classification report')
print(metrics.classification_report(rf_saf_gs_prediction, y_test))