Pratyush

gistfile1.py

# Example using Decision Trees

import numpy as np
import matplotlib.pylab as plt
%matplotlib inline
all_data = []
with open("data.txt") as input_file:
    for line in input_file:
        all_data.append([item.replace('\r\n', '') for item in line.split('\t')[1:]])
X = np.vstack(all_data[1:11]).astype(float).transpose() # inputs
y = np.vstack(all_data[11:]).astype(float).transpose() # outputs
print X.shape, y.shape
from sklearn import cross_validation
from sklearn import preprocessing
# X = preprocessing.StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=.5)
from sklearn.tree import DecisionTreeRegressor
for depth in xrange(1, X.shape[1]):
    clf = DecisionTreeRegressor(max_depth=depth).fit(X_train, y_train)
    print 'Tree depth:', depth, 'Coefficient of determination, R^2: ', clf.score(X_test, y_test)
    
# Example using Neural Network
    
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD

all_data = []
with open("data.txt") as input_file:
    for line in input_file:
        all_data.append([item.replace('\r\n', '') for item in line.split('\t')[1:]])
X = np.vstack(all_data[1:11]).astype(float).transpose() # inputs
y = np.vstack(all_data[11:]).astype(float).transpose() # outputs
X = preprocessing.StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=.8)

batch_size = 1
n_input = 10
n_hidden = 2
n_output = 24

model = Sequential()
model.add(Dense(n_input, n_hidden, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.1))
# model.add(Dense(n_hidden, n_hidden, init='uniform'))
# model.add(Activation('tanh'))
# model.add(Dropout(0.1))
model.add(Dense(n_hidden, n_output, init='uniform'))
model.add(Activation('softmax'))

sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=False)
model.compile(loss='mean_squared_error', optimizer=sgd)

model.fit(X_train, y_train, nb_epoch=10, batch_size=batch_size, verbose=2, show_accuracy=True)
score = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=2, show_accuracy=True)