I have built a small database of speeches that have been made over the past 40 years, I have scored these speeches in terms of their level of consideration based on the various parts of speech and words used. From this historic scoring I want to be able to score future speeches that are provided into a MySQL db via a web interface. I have attached the training data set as well as the test data set below.
I have tested the various models and SVM has the best R2 and lowest root mean squared deviation. The model may be overfit, due to the number of attributes I am using. I would appreciate your thoughts on that.
What I really need to find out if how to productionalise the SVM model into a MySQL/PHP type environment?
<?xml version="1.0" encoding="UTF-8"?><process version="9.7.002">
<context>
<input/>
<output/>
<macros>
<macro>
<key>label</key>
<value>Response</value>
</macro>
<macro>
<key>label_positive_class</key>
<value>yes</value>
</macro>
</macros>
</context>
<operator activated="true" class="process" compatibility="9.4.000" expanded="true" name="Process" origin="GENERATED_TEMPLATE">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<process expanded="true">
<operator activated="true" class="read_csv" compatibility="9.7.002" expanded="true" height="68" name="Read CSV" width="90" x="246" y="391">
<parameter key="csv_file" value="new.csv"/>
<parameter key="column_separators" value=";"/>
<parameter key="trim_lines" value="false"/>
<parameter key="use_quotes" value="true"/>
<parameter key="quotes_character" value="'"/>
<parameter key="escape_character" value="\"/>
<parameter key="skip_comments" value="true"/>
<parameter key="comment_characters" value="#"/>
<parameter key="starting_row" value="1"/>
<parameter key="parse_numbers" value="true"/>
<parameter key="decimal_character" value="."/>
<parameter key="grouped_digits" value="false"/>
<parameter key="grouping_character" value=","/>
<parameter key="infinity_representation" value=""/>
<parameter key="date_format" value=""/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="encoding" value="UTF-8"/>
<parameter key="read_all_values_as_polynominal" value="false"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="COL 1.true.real.attribute"/>
<parameter key="1" value="COL 2.true.real.attribute"/>
<parameter key="2" value="COL 3.true.real.attribute"/>
<parameter key="3" value="COL 4.true.real.attribute"/>
<parameter key="4" value="COL 5.true.real.attribute"/>
<parameter key="5" value="COL 6.true.real.attribute"/>
<parameter key="6" value="COL 7.true.real.attribute"/>
<parameter key="7" value="COL 8.true.real.attribute"/>
<parameter key="8" value="COL 9.true.real.attribute"/>
<parameter key="9" value="COL 10.true.real.attribute"/>
<parameter key="10" value="COL 11.true.real.attribute"/>
<parameter key="11" value="COL 12.true.real.attribute"/>
<parameter key="12" value="COL 13.true.real.attribute"/>
<parameter key="13" value="COL 14.true.real.attribute"/>
<parameter key="14" value="COL 15.true.real.attribute"/>
<parameter key="15" value="COL 16.true.real.attribute"/>
<parameter key="16" value="COL 17.true.real.attribute"/>
<parameter key="17" value="COL 18.true.real.attribute"/>
<parameter key="18" value="COL 19.true.real.attribute"/>
<parameter key="19" value="COL 20.true.real.attribute"/>
<parameter key="20" value="COL 21.true.real.attribute"/>
<parameter key="21" value="COL 22.true.real.attribute"/>
<parameter key="22" value="COL 23.true.real.attribute"/>
<parameter key="23" value="COL 24.true.real.attribute"/>
<parameter key="24" value="COL 25.true.real.attribute"/>
<parameter key="25" value="COL 26.true.real.attribute"/>
<parameter key="26" value="COL 27.true.real.attribute"/>
<parameter key="27" value="COL 28.true.real.attribute"/>
<parameter key="28" value="COL 29.true.real.attribute"/>
<parameter key="29" value="COL 30.true.real.attribute"/>
<parameter key="30" value="COL 31.true.real.attribute"/>
<parameter key="31" value="COL 32.true.real.attribute"/>
<parameter key="32" value="COL 33.true.real.attribute"/>
<parameter key="33" value="COL 34.true.real.attribute"/>
<parameter key="34" value="COL 35.true.real.attribute"/>
<parameter key="35" value="results\.request_id.true.polynominal.attribute"/>
<parameter key="36" value="name.true.polynominal.attribute"/>
<parameter key="37" value="url.true.polynominal.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="read_csv" compatibility="9.7.002" expanded="true" height="68" name="Read CSV (2)" width="90" x="45" y="187">
<parameter key="csv_file" value="training.csv"/>
<parameter key="column_separators" value=";"/>
<parameter key="trim_lines" value="false"/>
<parameter key="use_quotes" value="true"/>
<parameter key="quotes_character" value="""/>
<parameter key="escape_character" value="\"/>
<parameter key="skip_comments" value="true"/>
<parameter key="comment_characters" value="#"/>
<parameter key="starting_row" value="1"/>
<parameter key="parse_numbers" value="true"/>
<parameter key="decimal_character" value="."/>
<parameter key="grouped_digits" value="false"/>
<parameter key="grouping_character" value=","/>
<parameter key="infinity_representation" value=""/>
<parameter key="date_format" value=""/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="encoding" value="UTF-8"/>
<parameter key="read_all_values_as_polynominal" value="false"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="COL 1.true.real.attribute"/>
<parameter key="1" value="COL 2.true.real.attribute"/>
<parameter key="2" value="COL 3.true.real.attribute"/>
<parameter key="3" value="COL 4.true.real.attribute"/>
<parameter key="4" value="COL 5.true.real.attribute"/>
<parameter key="5" value="COL 6.true.real.attribute"/>
<parameter key="6" value="COL 7.true.real.attribute"/>
<parameter key="7" value="COL 8.true.real.attribute"/>
<parameter key="8" value="COL 9.true.real.attribute"/>
<parameter key="9" value="COL 10.true.real.attribute"/>
<parameter key="10" value="COL 11.true.real.attribute"/>
<parameter key="11" value="COL 12.true.real.attribute"/>
<parameter key="12" value="COL 13.true.real.attribute"/>
<parameter key="13" value="COL 14.true.real.attribute"/>
<parameter key="14" value="COL 15.true.real.attribute"/>
<parameter key="15" value="COL 16.true.real.attribute"/>
<parameter key="16" value="COL 17.true.real.attribute"/>
<parameter key="17" value="COL 18.true.real.attribute"/>
<parameter key="18" value="COL 19.true.real.attribute"/>
<parameter key="19" value="COL 20.true.real.attribute"/>
<parameter key="20" value="COL 21.true.real.attribute"/>
<parameter key="21" value="COL 22.true.real.attribute"/>
<parameter key="22" value="COL 23.true.real.attribute"/>
<parameter key="23" value="COL 24.true.real.attribute"/>
<parameter key="24" value="COL 25.true.real.attribute"/>
<parameter key="25" value="COL 26.true.real.attribute"/>
<parameter key="26" value="COL 27.true.real.attribute"/>
<parameter key="27" value="COL 28.true.real.attribute"/>
<parameter key="28" value="COL 29.true.real.attribute"/>
<parameter key="29" value="COL 30.true.real.attribute"/>
<parameter key="30" value="COL 31.true.real.attribute"/>
<parameter key="31" value="COL 32.true.real.attribute"/>
<parameter key="32" value="COL 33.true.real.attribute"/>
<parameter key="33" value="COL 34.true.real.attribute"/>
<parameter key="34" value="COL 35.true.real.attribute"/>
<parameter key="35" value="score.true.real.label"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="multiply" compatibility="9.7.002" expanded="true" height="103" name="Multiply" width="90" x="179" y="187"/>
<operator activated="true" class="concurrency:cross_validation" compatibility="8.2.000" expanded="true" height="145" name="Cross Validation" origin="GENERATED_TEMPLATE" width="90" x="45" y="493">
<parameter key="split_on_batch_attribute" value="false"/>
<parameter key="leave_one_out" value="false"/>
<parameter key="number_of_folds" value="10"/>
<parameter key="sampling_type" value="shuffled sampling"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="false" class="naive_bayes" compatibility="9.7.002" expanded="true" height="82" name="Naive Bayes" origin="GENERATED_TEMPLATE" width="90" x="45" y="34">
<parameter key="laplace_correction" value="true"/>
</operator>
<operator activated="true" class="support_vector_machine" compatibility="9.7.002" expanded="true" height="124" name="SVM" width="90" x="112" y="187">
<parameter key="kernel_type" value="dot"/>
<parameter key="kernel_gamma" value="1.0"/>
<parameter key="kernel_sigma1" value="1.0"/>
<parameter key="kernel_sigma2" value="0.0"/>
<parameter key="kernel_sigma3" value="2.0"/>
<parameter key="kernel_shift" value="1.0"/>
<parameter key="kernel_degree" value="2.0"/>
<parameter key="kernel_a" value="1.0"/>
<parameter key="kernel_b" value="0.0"/>
<parameter key="kernel_cache" value="200"/>
<parameter key="C" value="0.0"/>
<parameter key="convergence_epsilon" value="0.001"/>
<parameter key="max_iterations" value="1000000"/>
<parameter key="scale" value="true"/>
<parameter key="calculate_weights" value="true"/>
<parameter key="return_optimization_performance" value="true"/>
<parameter key="L_pos" value="1.0"/>
<parameter key="L_neg" value="1.0"/>
<parameter key="epsilon" value="0.0"/>
<parameter key="epsilon_plus" value="0.0"/>
<parameter key="epsilon_minus" value="0.0"/>
<parameter key="balance_cost" value="true"/>
<parameter key="quadratic_loss_pos" value="false"/>
<parameter key="quadratic_loss_neg" value="true"/>
<parameter key="estimate_performance" value="false"/>
</operator>
<connect from_port="training set" to_op="SVM" to_port="training set"/>
<connect from_op="SVM" from_port="model" to_port="model"/>
<connect from_op="SVM" from_port="exampleSet" to_port="through 1"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
<portSpacing port="sink_through 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="9.7.002" expanded="true" height="82" name="Apply Model (2)" origin="GENERATED_TEMPLATE" width="90" x="45" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance" compatibility="9.7.002" expanded="true" height="82" name="Performance" width="90" x="179" y="34">
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="performance 1"/>
<connect from_op="Performance" from_port="example set" to_port="test set results"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="source_through 2" spacing="0"/>
<portSpacing port="sink_test set results" spacing="0"/>
<portSpacing port="sink_performance 1" spacing="0"/>
<portSpacing port="sink_performance 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="9.7.002" expanded="true" height="82" name="Apply Model" origin="GENERATED_TEMPLATE" width="90" x="514" y="493">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="numerical_to_polynominal" compatibility="9.7.002" expanded="true" height="82" name="Numerical to Polynominal" width="90" x="380" y="187">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="score"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
</operator>
<operator activated="true" class="weight_by_information_gain" compatibility="9.7.002" expanded="true" height="82" name="Weight by Information Gain" width="90" x="514" y="187">
<parameter key="normalize_weights" value="false"/>
<parameter key="sort_weights" value="true"/>
<parameter key="sort_direction" value="ascending"/>
</operator>
<connect from_op="Read CSV" from_port="output" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Read CSV (2)" from_port="output" to_op="Multiply" to_port="input"/>
<connect from_op="Multiply" from_port="output 1" to_op="Numerical to Polynominal" to_port="example set input"/>
<connect from_op="Multiply" from_port="output 2" to_op="Cross Validation" to_port="example set"/>
<connect from_op="Cross Validation" from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_op="Cross Validation" from_port="example set" to_port="result 3"/>
<connect from_op="Cross Validation" from_port="test result set" to_port="result 4"/>
<connect from_op="Cross Validation" from_port="performance 1" to_port="result 5"/>
<connect from_op="Apply Model" from_port="labelled data" to_port="result 7"/>
<connect from_op="Apply Model" from_port="model" to_port="result 6"/>
<connect from_op="Numerical to Polynominal" from_port="example set output" to_op="Weight by Information Gain" to_port="example set"/>
<connect from_op="Weight by Information Gain" from_port="weights" to_port="result 1"/>
<connect from_op="Weight by Information Gain" from_port="example set" to_port="result 2"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="147"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
<portSpacing port="sink_result 4" spacing="0"/>
<portSpacing port="sink_result 5" spacing="0"/>
<portSpacing port="sink_result 6" spacing="0"/>
<portSpacing port="sink_result 7" spacing="0"/>
<portSpacing port="sink_result 8" spacing="0"/>
<description align="left" color="blue" colored="true" height="228" resized="true" width="317" x="20" y="105">Step 1:<br>Load and prepare data</description>
<description align="left" color="green" colored="true" height="224" resized="true" width="291" x="349" y="108">Step 2:<br>Determine which factors influence the model to improve prediction.</description>
<description align="left" color="green" colored="true" height="321" resized="true" width="442" x="198" y="340">Step 5:<br>Load new data for scoring</description>
<description align="left" color="yellow" colored="false" height="70" resized="true" width="850" x="20" y="25">Civility scorecard<br>Create a model that looks at scores related to the receptiviti model and predict what the final score will be</description>
<description align="left" color="yellow" colored="true" height="322" resized="true" width="176" x="18" y="339">Step 4:<br>Build and test model</description>
</process>
</operator>
</process>
