SGD.py

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import linear_model

df = pd.read_csv('data/BCHAIN.csv')

df_copy = df.copy()

#Not needed for prediction
df_copy.drop('Date', axis=1, inplace=True)

y = df_copy['Predict'].values
X = df_copy[['Value USD', 'Drop 7', 'Up 7', 'Mean Change 7', 'Change', 'Min 7', 'Max 7', 'Mean 7']].values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=42)

clf = linear_model.SGDClassifier()
clf.fit(X_train, y_train)

clf.score(X_test, y_test)
#Results
#0.4416826003824092