def get_train_data(limit=-1):
print('Loading train data')
X,y = rd.read_train(limit=limit)
print('Augmenting data set')
X,y = rd.nudge_dataset(X,y)
print('Scaling data')
X = scale(X)
return X,y
def get_train_data(limit=-1):
print('Loading train data')
X, y = rd.read_train(limit=limit)
print('Augmenting data set')
X, y = rd.nudge_dataset(X, y)
print('Scaling data')
X = scale(X)
return X, y
def classifyRF(train_file="train.csv", test_file ="test.csv", trees=70):
#So, let's classifiy this thing. Reading the Features and then the test.
print("Reading train data")
X,y = rd.read_train(file_name=train_file)
print("Augmenting dataset")
X,y = rd.nudge_dataset(X,y)
print("Reading test data")
test_data = rd.read_test(file_name=test_file)
#Creating the classifier. It has a ton of parameters, but since this a hard and fast one, here you go.
rfc = RandomForestClassifier(trees)
#Train with the data we have. Cry a little inside.
print("Training classifier")
rfc.fit(X, y)
predictions = rfc.predict(test_data)
#Most submitions are cute with a CSV. Might as well learn how to do it.
pd.DataFrame({"ImageId": range(1,len(predictions)+1), "Label": predictions}).to_csv('submit.csv', index=False, header=True)
def classifyRF(train_file="train.csv", test_file="test.csv", trees=70):
#So, let's classifiy this thing. Reading the Features and then the test.
print("Reading train data")
X, y = rd.read_train(file_name=train_file)
print("Augmenting dataset")
X, y = rd.nudge_dataset(X, y)
print("Reading test data")
test_data = rd.read_test(file_name=test_file)
#Creating the classifier. It has a ton of parameters, but since this a hard and fast one, here you go.
rfc = RandomForestClassifier(trees)
#Train with the data we have. Cry a little inside.
print("Training classifier")
rfc.fit(X, y)
predictions = rfc.predict(test_data)
#Most submitions are cute with a CSV. Might as well learn how to do it.
pd.DataFrame({
"ImageId": range(1,
len(predictions) + 1),
"Label": predictions
}).to_csv('submit.csv', index=False, header=True)
#Let's test out what number of trees is best on a forest!
import numpy as np
import read_dataset as rd
import evaluation as e
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
# loading training data
print('Loading training data')
X,y = rd.read_train()
X,y = rd.nudge_dataset(X,y)
scores = []
scores_std = []
#just so we know it didn't blow up or something
print('Start learning...')
#The last few might be excessive.
forests = [10, 15, 20, 25, 30, 40, 50, 70, 100, 125, 150, 175, 200, 250]
for tree in forests:
print("This forest has {} trees!".format(tree))
classifier = RandomForestClassifier(tree)
#score = cross_validation.cross_val_score(classifier, X, y)
#scores.append(np.mean(score))
#scores_std.append(np.std(score))
name = "plots_extended/RandomForest_{}_trees.png".format(tree)
e.evaluate_classifier(classifier,X,y, name=name)
#print('Score: ', np.array(scores))
#print('Std : ', np.array(scores_std))
#Let's test out what number of trees is best on a forest!
import numpy as np
import read_dataset as rd
import evaluation as e
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
# loading training data
print('Loading training data')
X, y = rd.read_train()
X, y = rd.nudge_dataset(X, y)
scores = []
scores_std = []
#just so we know it didn't blow up or something
print('Start learning...')
#The last few might be excessive.
forests = [10, 15, 20, 25, 30, 40, 50, 70, 100, 125, 150, 175, 200, 250]
for tree in forests:
print("This forest has {} trees!".format(tree))
classifier = RandomForestClassifier(tree)
#score = cross_validation.cross_val_score(classifier, X, y)
#scores.append(np.mean(score))
#scores_std.append(np.std(score))
name = "plots_extended/RandomForest_{}_trees.png".format(tree)
e.evaluate_classifier(classifier, X, y, name=name)
#print('Score: ', np.array(scores))
#print('Std : ', np.array(scores_std))