flink-ml-python/pyflink/examples/ml/feature/idf_example.py

################################################################################
#  Licensed to the Apache Software Foundation (ASF) under one
#  or more contributor license agreements.  See the NOTICE file
#  distributed with this work for additional information
#  regarding copyright ownership.  The ASF licenses this file
#  to you under the Apache License, Version 2.0 (the
#  "License"); you may not use this file except in compliance
#  with the License.  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
# limitations under the License.
################################################################################

# Simple program that trains an IDF model and uses it for feature
# engineering.

from pyflink.common import Types
from pyflink.ml.linalg import Vectors, DenseVectorTypeInfo
from pyflink.datastream import StreamExecutionEnvironment
from pyflink.ml.feature.idf import IDF
from pyflink.table import StreamTableEnvironment

# Creates a new StreamExecutionEnvironment.
env = StreamExecutionEnvironment.get_execution_environment()

# Creates a StreamTableEnvironment.
t_env = StreamTableEnvironment.create(env)

# Generates input for training and prediction.
input_table = t_env.from_data_stream(
    env.from_collection([
        (Vectors.dense(0, 1, 0, 2),),
        (Vectors.dense(0, 1, 2, 3),),
        (Vectors.dense(0, 1, 0, 0),),
    ],
        type_info=Types.ROW_NAMED(
            ['input', ],
            [DenseVectorTypeInfo(), ])))

# Creates an IDF object and initializes its parameters.
idf = IDF().set_min_doc_freq(2)

# Trains the IDF Model.
model = idf.fit(input_table)

# Uses the IDF Model for predictions.
output = model.transform(input_table)[0]

# Extracts and displays the results.
field_names = output.get_schema().get_field_names()
for result in t_env.to_data_stream(output).execute_and_collect():
    input_index = field_names.index(idf.get_input_col())
    output_index = field_names.index(idf.get_output_col())
    print('Input Value: ' + str(result[input_index]) +
          '\tOutput Value: ' + str(result[output_index]))