- 博客(7)
- 收藏
- 关注
RSS订阅原创 Algorithm Test Harnesses
Chapter 6Algorithm Test Harnesses训练集测试算法测试工具# Example of a Train-Test Test Harness from random import seed from random import randrange from csv import reader# Load a CSV file def load_csv(fi...
2020-04-20 09:41:29
177
原创 Baseline Models
Chapter 5Baseline Models随机预测算法# Example of Making Random Predictions from random import seed from random import randrang# Generate random predictions def random_algorithm(train, test): outpu...
2020-04-18 13:45:52
451
原创 Evaluation Metrics
chap4评价指标分类精度# Calculate accuracy percentage between two lists def accuracy_metric(actual, predicted): correct = 0 for i in range(len(actual)): if actual[i] == predicted[i]: correct += 1 ...
2020-04-18 13:17:45
216
原创 Algorithm Evaluation Methods
Chapter 3Algorithm Evaluation MethodsTrain and Test Split# Split a dataset into a train and test setdef train_test_split(dataset,split=0.60): train = list() train_size = split * len(dataset) d...
2020-04-17 12:31:18
171
原创 Scale Machine Learning Data
Chapter 2Scale Machine Learning Data标准化数据得到最大值和最小值# Find the min and max values for each column def dataset_minmax(dataset): minmax = list() for i in range(len(dataset[0])): col_values = ...
2020-04-17 12:11:30
89
原创 Load Data From CSV
chap1从csv中加载数据集加载csv文件# Load a CSV file def load_csv(filename): file = open(filename, "r") lines = reader(file) dataset = list(lines) return dataset其中，len(dataset)表示行数, len(dataset[0]))表示列...
2020-04-17 11:30:48
638
原创 神经网络学习----batch和epoch的理解
理解batch是一次处理的数据集，在训练的时候，将batch个数据的损失取平均，用于梯度下降算法。epoch是训练的次数，每次epoch会完成 样本数量/batch 的反向传播，更新参数实例假设有一个包含200个样本的数据集，选择的Batch大小为5和1,000个Epoch。则共有40个Batch，每个Batch有5个样本。每批五个样品后，模型权重将更新。一个epoch将涉及40个Ba...
2020-04-15 16:34:32
644
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人