In [1]:

    

## imports,
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

import models.imports.features

sns.set()


    

In [2]:

    

## load in features df.

trainsf_ = r'../data/text/bitcoin/train_set.csv'
train_set = models.imports.features.import_file(trainsf_)
train_set_x, train_set_y = models.imports.features.scale_and_transform_into_datasets(train_set)


    

In [3]:

    

from sklearn.tree import DecisionTreeRegressor


    

In [4]:

    

model = DecisionTreeRegressor()
model.fit(train_set_x.values, train_set_y.values.ravel())


    

    
Out[4]:





DecisionTreeRegressor(criterion='mse', max_depth=None, max_features=None,
           max_leaf_nodes=None, min_impurity_decrease=0.0,
           min_impurity_split=None, min_samples_leaf=1,
           min_samples_split=2, min_weight_fraction_leaf=0.0,
           presort=False, random_state=None, splitter='best')

In [5]:

    

prediction = model.predict(train_set_x)

mse = models.imports.features.mse(train_set_y.values, prediction)
print('mse:', mse)


    

    




mse: 0.07618257265733992

In [6]:

    

plt.plot(prediction, 'ro', markersize=1)
plt.plot(train_set_y, 'b', alpha=.3)
plt.show()


    

In [7]:

    

## test,

testsf_ = r'../data/text/bitcoin/test_set.csv'
test_set = models.imports.features.import_file(testsf_)
test_set_x, test_set_y = models.imports.features.scale_and_transform_into_datasets(test_set)


    

In [8]:

    

## mean squared error,

test_prediction = model.predict(test_set_x)
mse_test = models.imports.features.mse(test_set_y.values, test_prediction)
print('mse:', mse_test)


    

    




mse: 0.09632266998479229

In [9]:

    

plt.plot(model.predict(test_set_x), 'ro', markersize=1)
plt.plot(test_set_y, 'b', alpha=.3)
plt.show()


    

In [ ]: