Tensorflow:如何为 numpy 矩阵输入创建 feature_columns [英] Tensorflow: how to create feature_columns for numpy matrix input

问题描述

我使用的是 tensorflow 1.8.0，python 3.6.5.数据为虹膜数据集.代码如下:

I'm using tensorflow 1.8.0, python 3.6.5. The data is iris data set. Here is the code:

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import tensorflow as tf

X = iris['data']
y = iris['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

input_train=tf.estimator.inputs.numpy_input_fn(x=X_train,
            y=y_train, num_epochs=100, shuffle=False)
classifier_model = tf.estimator.DNNClassifier(hidden_units=[10, 
                  20, 10], n_classes=3, feature_columns=??)

这是我的问题，如何为 numpy 矩阵设置 feature_columns?

Here is my problem, how do I setup the feature_columns for a numpy matrix?

如果我将 X 和 y 转换为 pandas.DataFrame，我可以对 feature_columns 使用以下代码，并且它可以在 DNNClassifier 模型中使用.

If I covert the X and y to pandas.DataFrame, I can use the following code for the feature_columns, and it works in the DNNClassifier model.

features = X.columns
feature_columns = [tf.feature_column.numeric_column(key=key) for key in features]

推荐答案

您可以将 numpy ndarray 包装在字典中并将其作为输入 x 传递给 numpy_input_fn 方法和然后使用该字典中的键来定义您的 feature_column.还要注意的是，由于您的X_train 中的每个数据都有 4 个维度，因此您需要在定义 tf.feature_column.numeric_column 时指定 shape 参数.完整代码如下:

You can wrap your numpy ndarray in a dictionary and pass it to numpy_input_fn method as input x and then use the key in that dictionary to define your feature_column. Also note that because each data in your X_train has 4 dimensions, you need to specify the shape parameter when defining tf.feature_column.numeric_column. Here is the completed code:

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import tensorflow as tf

iris = load_iris()

X = iris['data']
y = iris['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

input_train = tf.estimator.inputs.numpy_input_fn(
                  x = {'x': X_train},
                  y = y_train,
                  num_epochs = 100,
                  shuffle = False)

feature_columns = [tf.feature_column.numeric_column(key='x', shape=(X_train.shape[1],))]

classifier_model = tf.estimator.DNNClassifier(
                       hidden_units=[10, 20, 10],
                       n_classes=3,
                       feature_columns=feature_columns)

这篇关于Tensorflow:如何为 numpy 矩阵输入创建 feature_columns的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！