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

# In[1]:


#Carga de las librerías
import urllib.request
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier


# In[2]:


#Descargamos los datos desde internet!
file_name = 'dataR2.csv'

def download_file(file_name):
    print('Descargando el dataset')
    url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00451/dataR2.csv'
    urllib.request.urlretrieve(url, file_name)


download_file(file_name)


# In[3]:


#Ahora si cargamos los datos en jupyter!
data = pd.read_csv(file_name)
data.head()


# **Insights**:
# 
# * El dataset se compone de 10 columnas de las cuales 9 corresponden a variables independientes, que usaremos para predecir el target. 
# 
# * Classification es la variable a predecir. Todas las variables son numéricas, ya sea enteras o reales y no tiene valores nulos.

# In[4]:


#Separamos en X e y
X = data.drop(["Classification"], axis=1)
y = data["Classification"]


# In[5]:


#Separamos en train y test!
(X_train, X_test,y_train, y_test) = train_test_split(X,y,stratify=y,test_size=0.30,random_state=42)


# In[6]:


#Creamos un arbol de decisión sencillo y lo fiteamos
tree = DecisionTreeClassifier(random_state=42)
tree.fit(X_train, y_train)


# In[7]:


y_test_pred = tree.predict(X_test) #Prediccion en 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[8]:


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


# 2. Crear la Matriz de Confusión

# In[9]:


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


# 3. Calcular la métrica Recall

# In[10]:


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


# 4.Calcular la métrica F1 score

# In[11]:


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


# In[12]:


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


# # Random Forest

# In[13]:


#Creamos un random forest!
model = RandomForestClassifier(random_state=42, n_estimators=100,
                               class_weight="balanced", max_features="log2")
model.fit(X_train, y_train)


# In[14]:


y_test_pred = model.predict(X_test) #Prediccion en Test


# 1. Calcular la métrica Accuracy.

# In[15]:


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


# 2. Calcular la métrica Precision

# In[16]:


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


# 3. Calcular la métrica Recall

# In[17]:


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


# 4. Calcular la métrica F1 score

# In[18]:


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


# <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>