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

# # Xgboost - Clasificación

# In[7]:


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


# In[2]:


get_ipython().system('pip install xgboost')


# In[8]:


import xgboost as xgb #pip install xgboost
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression as LR
from sklearn.model_selection import train_test_split

data = pd.read_csv('winequality-red.csv')
data


# In[9]:


data.quality.unique()


# Vamos a hacer un problema de clasificacion. Asi que lo que vamos a predecir es
# si el vino es de buena calidad o no. Tomaremos el 6 como umbral para decidir si
# es bueno o no. 

# In[10]:


data.loc[data['quality'] < 6, 'quality'] = 0 #baja calidad
data.loc[data['quality'] >= 6, 'quality'] = 1 #alta calidad


# In[11]:


#Veamos que tenemos!
data


# In[12]:


X = data.drop("quality", axis=1) #Elimino de mi dataset la variable a predecir
y = data.quality #Defino el Target


# In[13]:


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=123)


# In[14]:


clf_xgb = xgb.XGBClassifier(objective='binary:logistic', n_estimators=10,seed=42,max_depth=6, learning_rate=0.01)


# In[15]:


clf_xgb.fit(X_train,y_train) #Entrenamos el modelo


# In[16]:


y_train_pred = clf_xgb.predict(X_train) #Prediccion en Train
y_test_pred = clf_xgb.predict(X_test) #Prediccion en Test


# In[17]:


from sklearn.metrics import accuracy_score

#Calculo el accuracy en Train
#train_accuracy = accuracy_score(y_train, y_train_pred)

#Calculo el accuracy en Test
test_accuracy = accuracy_score(y_test, y_test_pred)

#print('% de aciertos sobre el set de entrenamiento:', train_accuracy)
print('% de aciertos sobre el set de evaluación:',test_accuracy)


# # XGboost - Regresión

# In[18]:


import pandas as pd
import xgboost as xgb
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error


# In[19]:


boston = load_boston()
X = pd.DataFrame(boston.data, columns=boston.feature_names)
y = pd.Series(boston.target)


# In[21]:


#Vemos que tenemos!
X.head()


# In[22]:


y


# In[23]:


#Creamos el objeteo XGBoost
regressor = xgb.XGBRegressor(
    n_estimators=80,
    reg_lambda=1, # L1 regularization term on weights
    gamma=0, # Minimum loss reduction required to make a further partition on a leaf node of the tree
    max_depth=3
)


# In[24]:


#Fiteamos
regressor.fit(X_train, y_train)


# In[25]:


#Predecimos
y_pred = regressor.predict(X_test)


# In[26]:


#Error
mean_squared_error(y_test, y_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,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHN2ZyB3aWR0aD0iODBweCIgaGVpZ2h0PSI4MHB4IiB2aWV3Qm94PSIwIDAgODAgODAiIHZlcnNpb249IjEuMSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIiB4bWxuczp4bGluaz0iaHR0cDovL3d3dy53My5vcmcvMTk5OS94bGluayI+CiAgICA8IS0tIEdlbmVyYXRvcjogU2tldGNoIDU0LjEgKDc2NDkwKSAtIGh0dHBzOi8vc2tldGNoYXBwLmNvbSAtLT4KICAgIDx0aXRsZT5Hcm91cCAzPC90aXRsZT4KICAgIDxkZXNjPkNyZWF0ZWQgd2l0aCBTa2V0Y2guPC9kZXNjPgogICAgPGcgaWQ9IkxhbmRpbmciIHN0cm9rZT0ibm9uZSIgc3Ryb2tlLXdpZHRoPSIxIiBmaWxsPSJub25lIiBmaWxsLXJ1bGU9ImV2ZW5vZGQiPgogICAgICAgIDxnIGlkPSJBcnRib2FyZCIgdHJhbnNmb3JtPSJ0cmFuc2xhdGUoLTEyMzUuMDAwMDAwLCAtNzkuMDAwMDAwKSI+CiAgICAgICAgICAgIDxnIGlkPSJHcm91cC0zIiB0cmFuc2Zvcm09InRyYW5zbGF0ZSgxMjM1LjAwMDAwMCwgNzkuMDAwMDAwKSI+CiAgICAgICAgICAgICAgICA8cG9seWdvbiBpZD0iUGF0aC0yMCIgZmlsbD0iIzAyNjVCNCIgcG9pbnRzPSIyLjM3NjIzNzYyIDgwIDM4LjA0NzY2NjcgODAgNTcuODIxNzgyMiA3My44MDU3NTkyIDU3LjgyMTc4MjIgMzIuNzU5MjczOSAzOS4xNDAyMjc4IDMxLjY4MzE2ODMiPjwvcG9seWdvbj4KICAgICAgICAgICAgICAgIDxwYXRoIGQ9Ik0zNS4wMDc3MTgsODAgQzQyLjkwNjIwMDcsNzYuNDU0OTM1OCA0Ny41NjQ5MTY3LDcxLjU0MjI2NzEgNDguOTgzODY2LDY1LjI2MTk5MzkgQzUxLjExMjI4OTksNTUuODQxNTg0MiA0MS42NzcxNzk1LDQ5LjIxMjIyODQgMjUuNjIzOTg0Niw0OS4yMTIyMjg0IEMyNS40ODQ5Mjg5LDQ5LjEyNjg0NDggMjkuODI2MTI5Niw0My4yODM4MjQ4IDM4LjY0NzU4NjksMzEuNjgzMTY4MyBMNzIuODcxMjg3MSwzMi41NTQ0MjUgTDY1LjI4MDk3Myw2Ny42NzYzNDIxIEw1MS4xMTIyODk5LDc3LjM3NjE0NCBMMzUuMDA3NzE4LDgwIFoiIGlkPSJQYXRoLTIyIiBmaWxsPSIjMDAyODY4Ij48L3BhdGg+CiAgICAgICAgICAgICAgICA8cGF0aCBkPSJNMCwzNy43MzA0NDA1IEwyNy4xMTQ1MzcsMC4yNTcxMTE0MzYgQzYyLjM3MTUxMjMsLTEuOTkwNzE3MDEgODAsMTAuNTAwMzkyNyA4MCwzNy43MzA0NDA1IEM4MCw2NC45NjA0ODgyIDY0Ljc3NjUwMzgsNzkuMDUwMzQxNCAzNC4zMjk1MTEzLDgwIEM0Ny4wNTUzNDg5LDc3LjU2NzA4MDggNTMuNDE4MjY3Nyw3MC4zMTM2MTAzIDUzLjQxODI2NzcsNTguMjM5NTg4NSBDNTMuNDE4MjY3Nyw0MC4xMjg1NTU3IDM2LjMwMzk1NDQsMzcuNzMwNDQwNSAyNS4yMjc0MTcsMzcuNzMwNDQwNSBDMTcuODQzMDU4NiwzNy43MzA0NDA1IDkuNDMzOTE5NjYsMzcuNzMwNDQwNSAwLDM3LjczMDQ0MDUgWiIgaWQ9IlBhdGgtMTkiIGZpbGw9IiMzNzkzRUYiPjwvcGF0aD4KICAgICAgICAgICAgPC9nPgogICAgICAgIDwvZz4KICAgIDwvZz4KPC9zdmc+' > </img>
# Created in <span style='font-weight:600;margin-left:4px;'>Deepnote</span></a>