predictor2.py

from sklearn.ensemble import RandomForestClassifier

X = df[['Open', 'Max 7', 'Min 7', 'Change', 'Mean Change 7', 'Drop 7', 'Up 7']].values
y = df['Actual'].values

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

clf = RandomForestClassifier(max_depth=2, random_state=0)
clf.fit(X_train, y_train)

# RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
#             max_depth=2, max_features='auto', 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, n_estimators=10, n_jobs=1,
#             oob_score=False, random_state=0, verbose=0, warm_start=False)

clf.score(X_test, y_test)
#0.9390862944162437

df2 = pd.read_csv('data/AAPL-edited2.csv')

X2 = df2[['Open', 'Max 7', 'Min 7', 'Change', 'Mean Change 7', 'Drop 7', 'Up 7']].values
y2 = df2['Actual'].values

clf.score(X2, y2)
#0.4176334106728538