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

# ## Regression with AdaBoost regressor

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np

from sklearn import ensemble, datasets, metrics, model_selection


# In[2]:


boston = datasets.load_boston()
print(boston.DESCR)


# In[3]:


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


# In[4]:


X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, train_size=0.7)

print('train samples:', len(X_train))
print('test samples', len(X_test))


# In[5]:


df_train = pd.DataFrame(y_train, columns=['target'])
df_train['type'] = 'train'

df_test = pd.DataFrame(y_test, columns=['target'])
df_test['type'] = 'test'

df_set = df_train.append(df_test)

_ = sns.displot(df_set, x="target" ,hue="type", kind="kde", log_scale=False)


# In[6]:


model = ensemble.AdaBoostRegressor(n_estimators=50)
model.fit(X_train, y_train)


# In[7]:


predicted = model.predict(X_test)

fig, ax = plt.subplots()
ax.scatter(y_test, predicted)

ax.set_xlabel('True Values')
ax.set_ylabel('Predicted')
_ = ax.plot([0, y.max()], [0, y.max()], ls='-', color='red')


# In[8]:


residual = y_test - predicted

fig, ax = plt.subplots()
ax.scatter(y_test, residual)
ax.set_xlabel('y')
ax.set_ylabel('residual')

_ = plt.axhline(0, color='red', ls='--')


# In[9]:


_ = sns.displot(residual, kind="kde");


# In[10]:


print("r2 score: {}".format(metrics.r2_score(y_test, predicted)))
print("mse: {}".format(metrics.mean_squared_error(y_test, predicted)))
print("rmse: {}".format(np.sqrt(metrics.mean_squared_error(y_test, predicted))))
print("mae: {}".format(metrics.mean_absolute_error(y_test, predicted)))