def run_census(flags_obj):
"""Construct all necessary functions and call run_loop.
Args:
flags_obj: Object containing user specified flags.
"""
if flags_obj.download_if_missing:
census_dataset.download(flags_obj.data_dir)
train_file = os.path.join(flags_obj.data_dir, census_dataset.TRAINING_FILE)
test_file = os.path.join(flags_obj.data_dir, census_dataset.EVAL_FILE)
# Train and evaluate the model every `flags.epochs_between_evals` epochs.
def train_input_fn():
return census_dataset.input_fn(
train_file, flags_obj.epochs_between_evals, True, flags_obj.batch_size)
def eval_input_fn():
return census_dataset.input_fn(test_file, 1, False, flags_obj.batch_size)
tensors_to_log = {
'average_loss': '{loss_prefix}head/truediv',
'loss': '{loss_prefix}head/weighted_loss/Sum'
}
wide_deep_run_loop.run_loop(
name="Census Income", train_input_fn=train_input_fn,
eval_input_fn=eval_input_fn,
model_column_fn=census_dataset.build_model_columns,
build_estimator_fn=build_estimator,
flags_obj=flags_obj,
tensors_to_log=tensors_to_log,
early_stop=True)
def run_census(flags_obj):
"""Construct all necessary functions and call run_loop.
Args:
flags_obj: Object containing user specified flags.
"""
if flags_obj.download_if_missing:
census_dataset.download(flags_obj.data_dir)
train_file = os.path.join(flags_obj.data_dir, census_dataset.TRAINING_FILE)
test_file = os.path.join(flags_obj.data_dir, census_dataset.EVAL_FILE)
# Train and evaluate the model every `flags.epochs_between_evals` epochs.
def train_input_fn():
return census_dataset.input_fn(
train_file, flags_obj.epochs_between_evals, True, flags_obj.batch_size)
def eval_input_fn():
return census_dataset.input_fn(test_file, 1, False, flags_obj.batch_size)
tensors_to_log = {
'average_loss': '{loss_prefix}head/truediv',
'loss': '{loss_prefix}head/weighted_loss/Sum'
}
wide_deep_run_loop.run_loop(
name="Census Income", train_input_fn=train_input_fn,
eval_input_fn=eval_input_fn,
model_column_fn=census_dataset.build_model_columns,
build_estimator_fn=build_estimator,
flags_obj=flags_obj,
tensors_to_log=tensors_to_log,
early_stop=True)
def main(unused_argvs):
TENSORFLOW_PATH = '/media/haoweiliu/Data/tensorflow/models'
models_path = os.path.join(TENSORFLOW_PATH, 'models')
sys.path.append(models_path)
from official.wide_deep import census_dataset
from official.wide_deep import census_main
census_dataset.download("./dataset/")
return 0
import tensorflow as tf
import tensorflow.feature_column as fc
import os
import sys
import matplotlib.pyplot as plt
tf.enable_eager_execution()
models_path = os.path.join(os.getcwd(), 'models')
sys.path.append(models_path)
from official.wide_deep import census_dataset
from official.wide_deep import census_main
census_dataset.download("/tmp/census_data/")
# export PYTHONPATH=${PYTHONPATH}:"$(pwd)/models"
# running from python you need to set the `os.environ` or the subprocess will not see the directory.
if "PYTHONPATH" in os.environ:
os.environ['PYTHONPATH'] += os.pathsep + models_path
else:
os.environ['PYTHONPATH'] = models_path
import pandas
train_df = pandas.read_csv(train_file,
header=None,
names=census_dataset._CSV_COLUMNS)
test_df = pandas.read_csv(test_file,
header=None,
import pandas
import functools
import numpy as np
tf.enable_eager_execution()
models_path = os.path.join(os.getcwd(), 'models')
sys.path.append(models_path)
from official.wide_deep import census_dataset
from official.wide_deep import census_main
# Download dataset
census_dataset.download("./dataset/")
train_file = "./dataset/adult.data"
test_file = "./dataset/adult.test"
# Read the U.S. Census data
train_df = pandas.read_csv(train_file,
header=None,
names=census_dataset._CSV_COLUMNS)
test_df = pandas.read_csv(test_file,
header=None,
names=census_dataset._CSV_COLUMNS)
train_df.head()
