%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

# use seaborn plotting defaults
# If this causes an error, you can comment it out.
import seaborn as sns
sns.set()

from astroML.datasets import fetch_rrlyrae_combined
from sklearn.cross_validation import train_test_split

X, y = fetch_rrlyrae_combined()

N_plot = 5000
plt.scatter(X[-N_plot:, 0], X[-N_plot:, 1], c=y[-N_plot:],
            edgecolors='none', cmap='RdBu')
plt.xlabel('u-g color')
plt.ylabel('g-r color')
plt.xlim(0.7, 1.4)
plt.ylim(-0.2, 0.4);

from sklearn.svm import SVC
SVC?

from sklearn.cross_validation import cross_val_score
cross_val_score?

from sklearn.cross_validation import train_test_split
Xsubset, _, ysubset, _ = train_test_split(X, y, train_size=0.1)

Xsubset.shape, ysubset.shape

model = SVC(kernel='linear', class_weight='auto')
cross_val_score(model, Xsubset, ysubset, scoring='f1')

C_values = 10 ** np.linspace(-2, 8, 10)
f1_scores = []

for C in C_values:
    model = SVC(kernel='linear', class_weight='auto', C=C)
    cv = cross_val_score(model, Xsubset, ysubset, scoring='f1')
    f1_scores.append(cv.mean())

plt.semilogx(C_values, f1_scores, '-k')

from sklearn.ensemble import RandomForestRegressor
RandomForestRegressor?

from astroML.datasets import fetch_sdss_specgals

data = fetch_sdss_specgals()

# put magnitudes in a matrix
feature_names = ['modelMag_%s' % f for f in 'ugriz']
X = np.vstack([data[f] for f in feature_names]).T
y = data['z']

# Plot some magnitudes for the first two thousand points
i, j = 0, 1
N = 2000
plt.scatter(X[:N, i], X[:N, j], c=y[:N],
            edgecolor='none', cmap='cubehelix')
plt.xlabel(feature_names[i])
plt.ylabel(feature_names[j])
plt.colorbar(label='redshift');