def train(self, X, y):
#check dimensions
if not len(X) == len(y):
raise IndexError("The number of samples in X and y do not match")
#check if X and y are numpy arrays
if type(X) is not np.ndarray:
X = self.__numpify(X)
if not X:
raise TypeError("input dataset X is not a valid numeric array")
if type(y) is not np.ndarray:
y = self.__numpify(y)
if not y:
raise TypeError("input label vector y is not a valid numeric array")
#check if trained
if self.trained:
self.__untrain()
indices = np.arange(len(X))
#determine the size of the bootstrap sample
strapsize = np.int(len(X)*self.fraction)
for t in xrange(self.n_trees):
#creat a new classification tree
tree = ClassificationTree(depth_limit=self.depth_limit, impurity=self.impurity)
#bootstrap a sample
bootstrap = np.random.choice(indices, strapsize)
Xstrap = X[bootstrap,:]
ystrap = y[bootstrap]
#train the t-th tree with the strapped sample
tree.train(Xstrap,ystrap)
self.trees[t] = tree
self.trained = True
print("%d trees grown" % self.n_trees)
def train(self, X, y):
#check dimensions
if not len(X) == len(y):
raise IndexError("The number of samples in X and y do not match")
#check if X and y are numpy arrays
if type(X) is not np.ndarray:
X = self.__numpify(X)
if not X:
raise TypeError("input dataset X is not a valid numeric array")
if type(y) is not np.ndarray:
y = self.__numpify(y)
if not y:
raise TypeError(
"input label vector y is not a valid numeric array")
#check if trained
if self.trained:
self.__untrain()
indices = np.arange(len(X))
#determine the size of the bootstrap sample
strapsize = np.int(len(X) * self.fraction)
for t in xrange(self.n_trees):
#creat a new classification tree
tree = ClassificationTree(depth_limit=self.depth_limit,
impurity=self.impurity)
#bootstrap a sample
bootstrap = np.random.choice(indices, strapsize)
Xstrap = X[bootstrap, :]
ystrap = y[bootstrap]
#train the t-th tree with the strapped sample
tree.train(Xstrap, ystrap)
self.trees[t] = tree
self.trained = True
print("%d trees grown" % self.n_trees)
def train(self, X, y):
# check dimensions
if not len(X) == len(y):
raise IndexError("The number of samples in X and y do not match")
# check if X and y are numpy arrays
if type(X) is not np.ndarray:
X = self.__numpify(X)
if not X:
raise TypeError("input dataset X is not a valid numeric array")
if type(y) is not np.ndarray:
y = self.__numpify(y)
if not y:
raise TypeError(
"input label vector y is not a valid numeric array")
# check if trained
if self.trained:
self.__untrain()
indices = np.arange(len(X))
# determine the size of the bootstrap sample
strapsize = np.int(len(X) * self.fraction)
features = np.arange(X.shape[1])
# determine the number of features to subsample each iteration
# using the sqrt(n) rule of thumb if n > 10
subsize = np.ceil(np.sqrt(X.shape[1])).astype(
np.int) if X.shape[1] >= 9 else X.shape[1]
# start growing the tree
for t in range(self.n_trees):
# creat a new classification tree
tree = ClassificationTree(depth_limit=self.depth_limit,
impurity=self.impurity)
# bootstrap a sample
bootstrap = np.random.choice(indices, strapsize)
subfeature = np.random.choice(
features, subsize,
replace=False) #features are not sampled with replacement
Xstrap = X[bootstrap, :][:, subfeature]
ystrap = y[bootstrap]
# train the t-th tree with the strapped sample
tree.train(Xstrap, ystrap)
# for each tree, need to save which features to use
self.trees[t] = [tree, subfeature]
self.trained = True
print("%d trees grown" % self.n_trees)
def train(self, X, y):
# check dimensions
if not len(X) == len(y):
raise IndexError("The number of samples in X and y do not match")
# check if X and y are numpy arrays
if type(X) is not np.ndarray:
X = self.__numpify(X)
if not X:
raise TypeError("input dataset X is not a valid numeric array")
if type(y) is not np.ndarray:
y = self.__numpify(y)
if not y:
raise TypeError("input label vector y is not a valid numeric array")
# check if trained
if self.trained:
self.__untrain()
indices = np.arange(len(X))
# determine the size of the bootstrap sample
strapsize = np.int(len(X)*self.fraction)
features = np.arange(X.shape[1])
# determine the number of features to subsample each iteration
# using the sqrt(n) rule of thumb if n > 10
subsize = np.ceil(np.sqrt(X.shape[1])).astype(np.int) if X.shape[1] >= 9 else X.shape[1]
# start growing the tree
for t in xrange(self.n_trees):
# creat a new classification tree
tree = ClassificationTree(depth_limit=self.depth_limit, impurity=self.impurity)
# bootstrap a sample
bootstrap = np.random.choice(indices, strapsize)
subfeature = np.random.choice(features, subsize, replace=False) #features are not sampled with replacement
Xstrap = X[bootstrap,:][:,subfeature]
ystrap = y[bootstrap]
# train the t-th tree with the strapped sample
tree.train(Xstrap,ystrap)
# for each tree, need to save which features to use
self.trees[t] = [tree, subfeature]
self.trained = True
print("%d trees grown" % self.n_trees)
__author__ = "metjush" # An example file for the decision_tree repository, using datasets from scikit-learn # to demonstrate classification with a single tree, bagged forest and random forest. # If you just want to see if the package works, run this file. # Importing all requirements import numpy as np from ClassTree import ClassificationTree from ClassTreeBagging import TreeBagger from ClassForest import RandomForest # Create the classifier objects tree = ClassificationTree() bag = TreeBagger(n_trees=50) forest = RandomForest(n_trees=50) # Get datasets from scikit-learn from sklearn.datasets import load_iris # iris classification # Save to arrays iris = load_iris() X_iris = iris.data y_iris = iris.target # Train classifiers with Iris data # Simple tree training tree.train(X_iris, y_iris)
if fileitem.filename:
# strip leading path
fn = os.path.basename(fileitem.filename)
filehash.update(fn)
name = filehash.hexdigest()
open(UPLOAD_DIR + name + ".csv", 'wb').write(fileitem.file.read())
savedfile = open(UPLOAD_DIR + name + ".csv", 'r')
else:
raise IOError("Upload of file failed")
# we will be returning a json file, so set header
message_header = "header('Content-type: application/json');"
# Import ClassificationTree class
from ClassTree import ClassificationTree
import numpy as np
# read the saved file as a numpy array
data = np.loadtxt(savedfile, delimiter=",")
X = np.concatenate((data[:,0:label_column], data[:,(label_column+1):]))
y = data[:,label_column]
train_tree = ClassificationTree(depth_limit=depth)
train_tree.train()
train_json = train_tree.to_json(JSON_DIR + name + ".json")
depth = form['depth']
label_column = form['label']
# checking
if fileitem.filename:
# strip leading path
fn = os.path.basename(fileitem.filename)
filehash.update(fn)
name = filehash.hexdigest()
open(UPLOAD_DIR + name + ".csv", 'wb').write(fileitem.file.read())
savedfile = open(UPLOAD_DIR + name + ".csv", 'r')
else:
raise IOError("Upload of file failed")
# we will be returning a json file, so set header
message_header = "header('Content-type: application/json');"
# Import ClassificationTree class
from ClassTree import ClassificationTree
import numpy as np
# read the saved file as a numpy array
data = np.loadtxt(savedfile, delimiter=",")
X = np.concatenate((data[:, 0:label_column], data[:, (label_column + 1):]))
y = data[:, label_column]
train_tree = ClassificationTree(depth_limit=depth)
train_tree.train()
train_json = train_tree.to_json(JSON_DIR + name + ".json")
__author__ = "metjush" # An example file for the decision_tree repository, using datasets from scikit-learn # to demonstrate classification with a single tree, bagged forest and random forest. # If you just want to see if the package works, run this file. # Importing all requirements import numpy as np from ClassTree import ClassificationTree from ClassTreeBagging import TreeBagger from ClassForest import RandomForest # Create the classifier objects tree = ClassificationTree() bag = TreeBagger(n_trees=50) forest = RandomForest(n_trees=50) # Get datasets from scikit-learn from sklearn.datasets import load_iris # iris classification # Save to arrays iris = load_iris() X_iris = iris.data y_iris = iris.target # Train classifiers with Iris data # Simple tree training tree.train(X_iris, y_iris)
import numpy as np
from ClassTree import ClassificationTree
from ClassTreeBagging import TreeBagger
from ClassForest import RandomForest
import sys
import string
import copy
from collections import Counter
from operator import itemgetter
# Create the classifier objects
tree = ClassificationTree()
bag = TreeBagger(n_trees=50)
forest = RandomForest(n_trees=50)
# Get datasets from scikit-learn
from sklearn.datasets import load_iris # iris classification
def process_str(s):
rem_punc = str.maketrans('', '', string.punctuation)
return s.translate(rem_punc).lower().split()
def read_dataset(file_name):
dataset = []
with open(file_name) as f:
for line in f:
index, class_label, text = line.strip().split('\t')
words = process_str(text)
dataset.append( (int(class_label), words) )
