sklearn_tree

import pandas as pd import matplotlib.pyplot as plt import numpy as np import seaborn as sns import re import numpy as np from sklearn import tree from sklearn.model_selection import train_test_split %matplotlib inline sns.set()

test_df = pd.read_csv('titanic-test.csv') train_df = pd.read_csv('titanic-train.csv')

train_df.head()

PassengerIdint64

Survivedint64

train_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

train_df.Sex.value_counts().plot(kind='bar',color=['b','r']) plt.title('Distribución de sobrevivientes') plt.show()

from sklearn import preprocessing label_encoder = preprocessing.LabelEncoder() encoder_sex = label_encoder.fit_transform(train_df['Sex']) train_df.head()

PassengerIdint64

Survivedint64

train_df['Age'] = train_df['Age'].fillna(train_df['Age'].median()) train_df['Embarked'] = train_df['Embarked'].fillna('S')

train_predictors = train_df.drop(['PassengerId','Survived','Name','Ticket','Cabin'], axis= 1) categorical_cols = [cname for cname in train_predictors.columns if train_predictors[cname].nunique() < 10 and train_predictors[cname].dtype == 'object' ]

numerical_cols = [cname for cname in train_predictors.columns if train_predictors[cname].dtype in ['int64', 'float64'] ]

my_cols = categorical_cols + numerical_cols train_predictors = train_predictors[my_cols]

dummy_encoded_train_predictors = pd.get_dummies(train_predictors)

train_df['Pclass'].value_counts()

y_target = train_df['Survived'].values x_features_one = dummy_encoded_train_predictors.values

X_train, X_validation, Y_train, Y_validation = train_test_split(x_features_one,y_target, test_size=0.25, random_state=1)

tree_one = tree.DecisionTreeClassifier() tree_one = tree_one.fit(x_features_one, y_target)

tree_one_accuracy = round(tree_one.score(x_features_one, y_target),4) print('Accuracy: %0.4f'%(tree_one_accuracy))

Accuracy: 0.9798

from io import StringIO from IPython.display import Image, display import pydotplus out=StringIO() tree.export_graphviz(tree_one, out_file=out) graph = pydotplus.graph_from_dot_data(out.getvalue()) graph.write_png('titanic.png')