devforfu

def build(self, graph=None, optimizer=None):
    """
    Creates model graph and groups important variables into named collections.
    """
    if graph is None:
        graph = tf.Graph()
    with graph.as_default():
        inputs = create_inputs()
        logits = build_model(
            inputs=inputs.x,

devforfu

def fit_generator(self, generator, epochs, batches_per_epoch,
                  validation_data=None, callbacks=None):
    """
    Fits model with generator yielding batches of (x, y) pairs.

    The generator is expected to indefinitely generate samples from
    training set. Therefore, we need a "hint" how much times we would like
    to call generator's `next()` method during single epoch. For this
    purpose `batches_per_epoch` parameter is used.
    """

devforfu

"""
Simple implementation of MNIST dataset classifier using TensforFlow and SGD.
"""
from os.path import expanduser

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

devforfu

def normalize_dataset(X):
    """
    Re-scales dataset to mean=0 and std=1.
    """
    X -= np.mean(X, axis=0)
    X /= np.clip(np.std(X, axis=0), 10e-6, np.inf)
    return X
  

def generate_random_centroids(n_features, n_clusters):

devforfu

def quantize(dataset_path, k):
    dataset = []
    
    for points in read_files(dataset_path):
        x = np.asarray(points, dtype=np.float)
        centroids, _ = kmeans(x, n_clusters=k)
        feature_vector = centroids.flatten()
        dataset.append(feature_vector)

    return np.array(dataset)

devforfu

def kmeans(dataset, k=5, num_of_restarts=10, max_iterations=300):
    """
    Runs K-Means clustering on dataset and returns the best 
    centroids assignemnt with its inertia score.
    """
    n_features = dataset.n_features
    norm_dataset = normalize_dataset(dataset)
    best_score = -np.inf
    best_centroids = None
        

devforfu

class RandomForestClassifier:

    def __init__(self, tree_funcs, n_trees: int=10,
                 feature_subset_size: str='sqrt', max_depth: int=5,
                 min_split_size: int=10, min_leaf_size: int=None,
                 log=None):

        if n_trees < 1:
            raise ValueError(f'cannot build an ensemble of {n_trees:d} trees')

devforfu

from os.path import join

import numpy as np
from sklearn.model_selection import train_test_split

from quantization import quantize
from decision_tree import learn_tree
from decision_tree import predict_tree
from ensemble import RandomForestClassifier
from utils import train_test_split, encode_labels

devforfu

"""
Wrist-Worn Accelerometer Dataset using scikit-learn.
"""

import re
from os import listdir
from os.path import exists, join, basename, isdir

import numpy as np

devforfu

"""
Main repository: https://github.com/devforfu/Blog/tree/master/trees
"""
import os
from os.path import join
from pprint import pprint

import pandas as pd
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler