comparison prepare_data.py @ 4:afec8c595124 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/recommendation_training/tools/tool_recommendation_model commit 65d36f271296a38deeceb0d0e8d471b2898ee8f4"

3:5b3c08710e47

import collections
import numpy as np
import random

import predict_tool_usage
import utils

main_path = os.getcwd()


class PrepareData:

        """
        Get the frequency of last tool of each tool sequence
        to estimate the frequency of tool sequences
        """
        last_tool_freq = dict()
        inv_freq = dict()
        for path in train_paths:
            last_tool = path.split(",")[-1]
            if last_tool not in last_tool_freq:
                last_tool_freq[last_tool] = 0
            last_tool_freq[last_tool] += 1
        max_freq = max(last_tool_freq.values())
        for t in last_tool_freq:
            inv_freq[t] = int(np.round(max_freq / float(last_tool_freq[t]), 0))
        return last_tool_freq, inv_freq

    def get_toolid_samples(self, train_data, l_tool_freq):
        l_tool_tr_samples = dict()
        for tool_id in l_tool_freq:
            for index, tr_sample in enumerate(train_data):

        multilabels_paths = self.prepare_paths_labels_dictionary(dictionary, rev_dict, all_unique_paths, compatible_next_tools)

        print("Complete data: %d" % len(multilabels_paths))
        train_paths_dict, test_paths_dict = self.split_test_train_data(multilabels_paths)

        # get sample frequency
        l_tool_freq, inv_last_tool_freq = self.get_train_last_tool_freq(train_paths_dict, rev_dict)

        print("Train data: %d" % len(train_paths_dict))
        print("Test data: %d" % len(test_paths_dict))

        print("Padding train and test data...")
        # pad training and test data with leading zeros
        test_data, test_labels = self.pad_paths(test_paths_dict, num_classes, standard_connections, rev_dict)
        train_data, train_labels = self.pad_paths(train_paths_dict, num_classes, standard_connections, rev_dict)

        l_tool_tr_samples = self.get_toolid_samples(train_data, l_tool_freq)

        # Predict tools usage
        print("Predicting tools' usage...")
        usage_pred = predict_tool_usage.ToolPopularity()

4:afec8c595124

import collections
import numpy as np
import random

import predict_tool_usage

main_path = os.getcwd()


class PrepareData:

        """
        Get the frequency of last tool of each tool sequence
        to estimate the frequency of tool sequences
        """
        last_tool_freq = dict()
        freq_dict_names = dict()
        for path in train_paths:
            last_tool = path.split(",")[-1]
            if last_tool not in last_tool_freq:
                last_tool_freq[last_tool] = 0
                freq_dict_names[reverse_dictionary[int(last_tool)]] = 0
            last_tool_freq[last_tool] += 1
            freq_dict_names[reverse_dictionary[int(last_tool)]] += 1
        return last_tool_freq

    def get_toolid_samples(self, train_data, l_tool_freq):
        l_tool_tr_samples = dict()
        for tool_id in l_tool_freq:
            for index, tr_sample in enumerate(train_data):

        multilabels_paths = self.prepare_paths_labels_dictionary(dictionary, rev_dict, all_unique_paths, compatible_next_tools)

        print("Complete data: %d" % len(multilabels_paths))
        train_paths_dict, test_paths_dict = self.split_test_train_data(multilabels_paths)

        print("Train data: %d" % len(train_paths_dict))
        print("Test data: %d" % len(test_paths_dict))

        print("Padding train and test data...")
        # pad training and test data with leading zeros
        test_data, test_labels = self.pad_paths(test_paths_dict, num_classes, standard_connections, rev_dict)
        train_data, train_labels = self.pad_paths(train_paths_dict, num_classes, standard_connections, rev_dict)

        print("Estimating sample frequency...")
        l_tool_freq = self.get_train_last_tool_freq(train_paths_dict, rev_dict)
        l_tool_tr_samples = self.get_toolid_samples(train_data, l_tool_freq)

        # Predict tools usage
        print("Predicting tools' usage...")
        usage_pred = predict_tool_usage.ToolPopularity()