【发布时间】：2020-11-21 19:58:53
【问题描述】：
我正在使用 tensorflow 运行流失模型并遇到 NaN 损失。仔细阅读，我发现我的数据中可能有一些 NaN 值，正如 print(np.any(np.isnan(X_test))) 所证实的那样。
我尝试过使用
def standardize(train, test):
mean = np.mean(train, axis=0)
std = np.std(train, axis=0)+0.000001
X_train = (train - mean) / std
X_test = (test - mean) /std
return X_train, X_test
但仍然会得出 NaN 值。
如果有帮助，这里是完整的代码：
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import tensorflow as tf
dataset = pd.read_excel('CHURN DATA.xlsx')
X = dataset.iloc[:, 2:45].values
y = dataset.iloc[:, 45].values
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
X[:, 1] = le.fit_transform(X[:,1])
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(),[0])], remainder = 'passthrough')
X = np.array(ct.fit_transform(X))
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
ann = tf.keras.models.Sequential()
ann.add(tf.keras.layers.Dense(units = 43, activation = 'relu'))
ann.add(tf.keras.layers.Dense(units = 43, activation = 'relu'))
ann.add(tf.keras.layers.Dense(units = 1, activation = 'sigmoid'))
ann.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
ann.fit(X_train, y_train, batch_size = 256, epochs = 50)
【问题讨论】：
-
在
dataset = pd.read_excel('CHURN DATA.xlsx')之后添加dataset = dataset.dropna() -
这行得通，但它丢弃了 80% 的数据。正如下面所建议的，我在某些输入中使用负值（透支的支票账户余额等）
-
它丢弃了 80% 的数据，因为 dropna 函数一旦找到 nan 就会删除整行，即使它只有一个。请改用 fillna。
标签： python tensorflow machine-learning nan