In [21]:
import pandas as pd
import platform
print 'python', platform.python_version()
print 'numpy', np.version.version
print 'pandas', pd.__version__
np.set_printoptions(linewidth =150)
In [22]:
smarket0 = pd.read_csv('data/Smarket.csv')
del smarket0['Unnamed: 0']
smarket0.head()
Out[22]:
In [23]:
smarket0.Direction.unique()
Out[23]:
In [24]:
smarket = smarket0.copy()
smarket['Direction'] = smarket.Direction == 'Up'
smarket.head()
Out[24]:
In [25]:
outcome = ['Direction']
factors = [col for col in smarket.columns if col != outcome[0]]
X = smarket[factors].as_matrix()
y = smarket[outcome].as_matrix().ravel()
In [26]:
_ = pd.tools.plotting.scatter_matrix(smarket, figsize=(14, 10))
In [27]:
from sklearn import linear_model
In [28]:
clf = linear_model.LogisticRegression()
clf.fit(X, y)
clf.coef_
Out[28]:
In [ ]: