feature\u列的项必须是\u FeatureColumn

你的第一个错误是如何创造 tf.estimator.LinearClassifier . 您正在传递数据帧索引 df.columns 进入 feature_columns ,但应通过 tensorflow feature columns . 列应该定义它是数字的还是分类的,在后一种情况下是编码类型。

其次,输入函数可以简化很多,因为你正在阅读 pandas 数据帧。只需使用 tf.estimator.inputs.pandas_input_fn .

你的 .csv 很可能是不同的,我做了一个有一些值的虚拟的。下面是一种读取输入并正确拟合模型的方法:

import pandas as pd
import tensorflow as tf

FEATURES = ["CreditScore", "Age", "Tenure", "Balance", "NumOfProducts", 
            "HasCrCard", "IsActiveMember", "EstimatedSalary", "Exited"]

credit_score = tf.feature_column.numeric_column("CreditScore")
age = tf.feature_column.numeric_column("Age")
tenure = tf.feature_column.numeric_column("Tenure")
balance = tf.feature_column.numeric_column("Balance")
num_of_products = tf.feature_column.numeric_column("NumOfProducts")
has_card = tf.feature_column.categorical_column_with_vocabulary_list("HasCrCard", ["True", "False"])
is_active_member = tf.feature_column.categorical_column_with_vocabulary_list("IsActiveMember", ["True", "False"])
estimated_salary = tf.feature_column.numeric_column("EstimatedSalary")
feature_columns = [credit_score, age, tenure, balance, num_of_products, has_card, is_active_member, estimated_salary]

def input_fn(num_epochs=None, shuffle=True, batch_size=100):
  df = pd.read_csv('Churn_Modelling.csv',
                   names=FEATURES,
                   dtype={'HasCrCard': str, 'IsActiveMember': str},
                   skipinitialspace=True,
                   header=0)
  df = df.dropna(how='any', axis=0)   # remove NaN elements
  labels = df["Exited"]
  return tf.estimator.inputs.pandas_input_fn(x=df,
                                             y=labels,
                                             batch_size=batch_size,
                                             num_epochs=num_epochs,
                                             shuffle=shuffle,
                                             num_threads=5)

model = tf.estimator.LinearClassifier(model_dir=None,
                                      feature_columns=feature_columns)
model.train(input_fn=input_fn(), steps=100)

它工作得很清楚。

import pandas as pd
import tensorflow as tf
import tempfile
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import cohen_kappa_score
from sklearn.metrics import f1_score
from sklearn.metrics import recall_score


def split_data(data, rate, label):
    data = data.dropna()

    train_data, test_data = train_test_split(data, test_size=rate)

    train_label = train_data[label]
    train_data = train_data.drop(label, 1)

    test_label = test_data[label]
    test_data = test_data.drop(label, 1)
    return train_data, train_label, test_data, test_label



LABEL = "Exited"

data = pd.read_csv("Churn_Modelling.csv", skipinitialspace=True, 
    header=0)

data.drop("Surname", axis=1, inplace=True)
data.drop("RowNumber", axis=1, inplace=True)
data.drop("CustomerId", axis=1, inplace=True)
data.drop("Geography", axis=1, inplace=True)
data.drop("Gender", axis=1, inplace=True)
x_train, y_train, x_test, y_test = split_data(data, 0.20, LABEL)



def get_input_fn_train():
    input_fn = tf.estimator.inputs.pandas_input_fn(
        x=x_train,
        y=y_train,
        shuffle=False
    )
    return input_fn

def get_input_fn_test():
    input_fn = tf.estimator.inputs.pandas_input_fn(
        x=x_test,
        y=y_test,
        shuffle=False
    )
    return input_fn


feature_columns = tf.contrib.learn.infer_real_valued_columns_from_input_fn
(get_input_fn_train())


model_dir = tempfile.mkdtemp()
m = tf.estimator.LinearClassifier(model_dir=model_dir, 
feature_columns=feature_columns)

# train data
m.train(input_fn=get_input_fn_train(), steps=5000)

# you can get accuracy, accuracy_baseline, auc, auc_precision_recall, 
#average_loss, global_step, label/mean, lossprediction/mean

results = m.evaluate(input_fn=get_input_fn_test(), steps=None)

print("model directory = %s" % model_dir)
for key in sorted(results):
    print("%s: %s" % (key, results[key]))

# get prediction results
y = m.predict(input_fn=get_input_fn_test())
predictions = list(y)
pred1=pd.DataFrame(data=predictions)
prediction=pd.DataFrame(data=pred1['class_ids'])
pred=[]
for row in prediction["class_ids"]:
    pred.append(row[0])

rowNumber = 0
for i in pred:
    print(str(rowNumber) + ': ' + str(i))
    rowNumber = rowNumber + 1


def calculate(prediction, LABEL):
    arr = {"accuracy": accuracy_score(prediction, LABEL),
           "report": classification_report(prediction, LABEL),
           "Confusion_Matrix": confusion_matrix(prediction, LABEL),
           "F1 score": f1_score(prediction, LABEL),
           "Recall Score": recall_score(prediction, LABEL),
           "cohen_kappa": cohen_kappa_score(prediction, LABEL)
           }
    return arr


pred2 = pd.DataFrame(data=pred)

print(calculate(pred2.round(), y_test))

suppressed warning 由于我的特殊硬件。

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import pandas as pd
import numpy as np
import tensorflow as tf

FEATURES = ["CreditScore", "Age", "Tenure", "Balance", "NumOfProducts", "EstimatedSalary", "Exited"]
credit_score = tf.feature_column.numeric_column("CreditScore")
age = tf.feature_column.numeric_column("Age")
tenure = tf.feature_column.numeric_column("Tenure")
balance = tf.feature_column.numeric_column("Balance")
num_of_products = tf.feature_column.numeric_column("NumOfProducts")
estimated_salary = tf.feature_column.numeric_column("EstimatedSalary")
feature_columns = [credit_score, age, tenure, balance, num_of_products, estimated_salary]

def input_fn(num_epochs=None, shuffle=True, batch_size=100):
  N_features = len(FEATURES)
  print(N_features)
  N_examples = 5000
  X_train = np.random.rand(N_examples,N_features)
  Y_train  = np.random.rand(N_examples)
  columns = [str(i) for i in range(N_features)]
  columns = FEATURES
  df = pd.DataFrame(data = X_train, columns = columns)
  labels = df["Exited"]
  return tf.estimator.inputs.pandas_input_fn(x=df,
                                             y=labels,
                                             batch_size=batch_size,
                                             num_epochs=num_epochs,
                                             shuffle=shuffle,
                                             num_threads=5)

model = tf.estimator.LinearClassifier(model_dir='model_dir',
                                      feature_columns=feature_columns)
model.train(input_fn=input_fn(), steps=100)