#!/usr/bin/env python
# coding: utf-8

# ### Árbol de Decisión modelo de Clasificación en Scikit-Learn - Titanic

# In[3]:


from google.colab import drive
import os
drive.mount('/content/gdrive')
# Establecer ruta de acceso en dr
import os
print(os.getcwd())
os.chdir("/content/gdrive/My Drive")


# In[4]:


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

titanic = pd.read_csv("Titanic.csv", sep = ",")


# In[5]:


titanic


# In[6]:


#Separación en Train y Test
X = titanic.drop("Survived", axis=1)
y = titanic.Survived


# In[7]:


from sklearn.model_selection import train_test_split 
#Train y Test Split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42) 


# In[8]:


#Arbol de Decision
from sklearn.tree import DecisionTreeClassifier 
arbol_de_decision = DecisionTreeClassifier(max_depth=4, random_state = 42) 


# In[9]:


#Fit
arbol_de_decision.fit(X_train,y_train) #Entrenamos el modelo


# In[10]:


#Prediccion
y_test_pred = arbol_de_decision.predict(X_test)


# In[11]:


y_test_pred


# In[12]:


y_test


# A lo largo de este notebook, se solicita calcular las métricas requeridas como así también su correspondiente interpretación: 
# 
# 1. Calcular la métrica Accuracy.

# In[13]:


###Completar
from sklearn.metrics import accuracy_score
accuracy_score(y_test,y_test_pred)


# 2. Crear la Matriz de Confusión

# In[14]:


###Completar
from sklearn.metrics import confusion_matrix
confusion_matrix(y_test, y_test_pred) 


# 3. Calcular la métrica Precision

# In[15]:


###Completar
from sklearn.metrics import precision_score
precision_score(y_test, y_test_pred) 


# 4. Calcular la métrica Recall

# In[16]:


###Completar
from sklearn.metrics import recall_score
recall_score(y_test, y_test_pred) 


# 5. Calcular la métrica F1 score

# In[17]:


###Completar
from sklearn.metrics import f1_score
f1_score(y_test, y_test_pred) 


# 6. classification_report

# In[18]:


from sklearn.metrics import classification_report
print(classification_report(y_test,y_test_pred))


# 6. Calcular y plotear la Curva ROC

# In[19]:


###Completar
from sklearn.metrics import roc_curve, roc_auc_score
import matplotlib.pyplot as plt

y_score1 = arbol_de_decision.predict_proba(X_test)[:,1]
y_score1


# In[20]:


# Calculo de tasas 
false_positive_rate1, true_positive_rate1, threshold1 = roc_curve(y_test, y_score1)


# In[21]:


print('roc_auc_score for DecisionTree: ', roc_auc_score(y_test, y_score1))


# In[22]:


plt.subplots(1, figsize=(8,6))
plt.title('Receiver Operating Characteristic - DecisionTree')
plt.plot(false_positive_rate1, true_positive_rate1)
plt.plot([0, 1], ls="--")
plt.plot([0, 0], [1, 0] , c=".7"), plt.plot([1, 1] , c=".7")
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
plt.show()


# <a style='text-decoration:none;line-height:16px;display:flex;color:#5B5B62;padding:10px;justify-content:end;' href='https://deepnote.com?utm_source=created-in-deepnote-cell&projectId=4f9037d8-f2e9-4683-9ce3-67576f784ec7' target="_blank">
# <img alt='Created in deepnote.com' style='display:inline;max-height:16px;margin:0px;margin-right:7.5px;' src='data:image/svg+xml;base64,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' > </img>
# Created in <span style='font-weight:600;margin-left:4px;'>Deepnote</span></a>