annotate pyspark/transforms/tonicHistogram.py @ 0:e34cf1b6fe09 tip

commit

# Part of DML (Digital Music Laboratory)
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# You should have received a copy of the GNU General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA

# -*- coding: utf-8 -*-
__author__="hargreavess"

from rdflib import Graph, Namespace, BNode, RDF, Literal
from n3Parser import get_rdf_graph_from_n3
from csvParser import get_dict_from_csv, get_array_from_csv

dml_ns = Namespace("http://dml.org/dml/cla#")

# Add triples representing a 'tonic histogram' result to
# an RDF graph
def add_tonic_histogram_to_graph(tonic_histogram, output_rdf_graph, transform, sample_count, input_f_files):

    output_bnode = BNode()
    output_rdf_graph.add((transform, dml_ns.output, output_bnode))
    for input_f_file in input_f_files:
        output_rdf_graph.add((transform, dml_ns.input, input_f_file))
    output_rdf_graph.add((output_bnode, RDF.type, dml_ns.TonicHistogram))
    output_rdf_graph.add((output_bnode, dml_ns.sample_count, Literal(sample_count)))

    for tonic in tonic_histogram:

        bin_bnode = BNode()
        output_rdf_graph.add((output_bnode, dml_ns.bin, bin_bnode))
        output_rdf_graph.add((bin_bnode, dml_ns.bin_number, Literal(tonic)))
        output_rdf_graph.add((bin_bnode, dml_ns.bin_value, Literal(tonic_histogram.get(tonic))))

    return output_rdf_graph

# Parse the input_f_files n3 files, and generate
# a tonic histogram
def find_cla_tonic_histogram(input_f_files):

    num_f_files = len(input_f_files)
    tonic_hist = dict()

    for x in range(1,13):

        tonic_hist[x] = 0

    for input_f_file in input_f_files:

#        tonic = find_last_key_in_piece(input_f_file)
        tonic = find_most_common_key_in_piece(input_f_file)
        tonic_hist[tonic] = tonic_hist.get(tonic) + 1

    return (tonic_hist, num_f_files)

def find_most_common_key_in_piece(input_f_file):
    
    tonic_hist = find_tonic_histogram(input_f_file)
    duration_of_tonic = max(tonic_hist.values())
    result = -1

    for tonic in tonic_hist:
        
        if tonic_hist[tonic] == duration_of_tonic:
            result = tonic
    
    return result

# Parse the input_f_files n3 file, and generate
# a tonic histogram
def find_tonic_histogram(input_f_file):

    tonic_hist = dict()

    for x in range(1,13):

        tonic_hist[x] = 0

    if input_f_file.endswith('.csv'):

        # ['time','keynr','label']
        csv_array = get_array_from_csv(input_f_file)

        for idx in range(1, len(csv_array)):

            tonic_duration = csv_array[idx][0] - csv_array[idx - 1][0]
            tonic = int(csv_array[idx - 1][1])
            tonic_hist[tonic] = tonic_hist.get(tonic) + tonic_duration
    
    else:

        # TODO - n3 version of tonic histogram
        # for now use last key in piece
        tonic = find_last_key_in_piece(input_f_file)
        tonic_hist[tonic] = tonic_hist.get(tonic) + 1

    return (tonic_hist)

# Determine the last (temporally) key in the
# input_f_file n3 file
def find_last_key_in_piece(input_f_file):

    max_time = 0
    last_key = 0

    if input_f_file.endswith('.csv'):

        csv_dict = get_dict_from_csv(input_f_file, columtype = ['time','keynr','label'])

        for row in csv_dict:
            
            tl_time = float(row['time'])
            
            if tl_time > max_time:
                
                max_time = tl_time
                last_key = row['keynr']
    
    
    else:

        key_feature_graph = get_rdf_graph_from_n3(input_f_file)
    
        qres = key_feature_graph.query(
            """prefix dml:     <http://dml.org/dml/cla#>
               prefix event: <http://purl.org/NET/c4dm/event.owl#>
               prefix tl: <http://purl.org/NET/c4dm/timeline.owl#>
               prefix af: <http://purl.org/ontology/af/>
                SELECT ?event ?key ?tl_time
                WHERE {
                    ?event event:time ?event_time .
                    ?event_time tl:at ?tl_time .
                    ?event af:feature ?key .
                }""")
    
        for row in qres:
    
            tl_time_str_len = len(row.tl_time)
            tl_time = float(row.tl_time[2:tl_time_str_len-1])
    
            if tl_time > max_time:
    
                max_time = tl_time
                last_key = row.key


    return int(last_key)