# Compare Algorithms
import pandas
import matplotlib.pyplot as plt
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.neural_network import MLPClassifier
from sklearn.cross_validation import train_test_split
from sklearn import datasets, metrics
import numpy as np

# load dataset
names = ['/column_names_in_my_csv_file']
dataframe = pandas.read_csv('/my_huge_csv_file', names=names)
array = dataframe.values
X = array[:,1:356]
Y = array[:,3568:3569]

X_train,X_test,y_train,y_test = train_test_split(X,Y,test_size=0.1)

nn01 = MLPClassifier(alpha=0.1, hidden_layer_sizes=100, random_state=1) # just test parameters for now...
nn02 = MLPClassifier(alpha=0.2, hidden_layer_sizes=400, random_state=1)

# evaluate each model in turn
results = []
names_val = []

y_tr = np.array(y_train).astype(int)
y_te = np.array(y_test).astype(int)

nn01.fit(X_train.astype(int), y_tr.astype(int))
predicted = nn01.predict(X_test.astype(int))

precision = metrics.average_precision_score(y_te.ravel(), predicted)

results.append(precision)
names_val.append("nn01")

msg = "%s: %f (%f)" % ("nn01", precision.mean(), precision.std())
print(msg)

nn02.fit(X_train.astype(int), y_tr.ravel())
predicted = nn02.predict(X_test)

precision = metrics.average_precision_score(y_te.ravel(), predicted)

results.append(precision)
names_val.append("nn02")

msg = "%s: %f (%f)" % ("nn02", precision.mean(), precision.std())
print(msg)

print results
# boxplot algorithm comparison
fig = plt.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names_val)
plt.show()