An Interest In:
Web News this Week
- March 22, 2024
- March 21, 2024
- March 20, 2024
- March 19, 2024
- March 18, 2024
- March 17, 2024
- March 16, 2024
Investigating Machine Learning Techniques to Improve Spec Tests IV
Intro
This is a part of the series of blog posts related to Artificial Intelligence Implementation. If you are interested in the background of the story or how it goes:
This week we'll showcase testing process and the early results of the model. We will be using SerpApi's Google Organic Results Scraper API for the data collection. Also, you can check in the playground in more detailed view on the data we will use.
Training Data
Here's an structural breakdown of the data we store for training inside a json file:
[ { "Key 1": Value_1, "Key 2": Value_2, "Key 3": Value_3, "Key 4": [ "Value_1", ... ], "Key 5": { "Inner Key 1": Inner_Value_1, ... }, ...]
Here's an example:
[ { "position": 1, "title": "Coffee - Wikipedia", "link": "https://en.wikipedia.org/wiki/Coffee", "displayed_link": "https://en.wikipedia.org wiki Coffee", "snippet": "Coffee is a brewed drink prepared from roasted coffee beans, the seeds of berries from certain flowering plants in the Coffea genus. From the coffee fruit, ...", "snippet_highlighted_words": [ "Coffee", "coffee", "coffee" ], ... }, ...]
Links we collected the organic results of Google from:
Link for Tea (around 100 results)
Link for Coffee (around 100 results)
Testing Structure
We have already covered how we trained the data in detail in the past three week's blog posts. Today, we will test how the hypothesis holds by calculating the training accuracy.
We can reutilize the Train
, and Database
classes to create examples, and create example vectors with the following lines:
example_vector = Database.word_to_tensor example example_vector.map! {|el| el = el.nil? ? 0: el} example_vector = Train.extend_vector example_vector weighted_example = Train.product example_vector
,example
in here is the string we provide. Any value for any key within Google Organic Results that is converted to a string will be a valid example.
We can reutilize Database.word_to_tensor
to get the vectorized version of our string in accordance with our vocabulary.
If any value is nil
(null), which is not present in our vocabulary, it will be replaced with 0
, which is the value for our <unk>
(unknown).example_vector
, then, should be expanded to maximum string size for calculation purposes using 1
s.weighted_example
will be the product of the @@weights
we calculated earlier with our vectorized example.
This value's closest vectors in multidimensional space, from the examples we provided, should have the same key, or their average should lead us to the same key. So, in our case, if the example we provide isn't a snippet
, closest vectors around the weighted_example
should give us less than 0.5
(their identities are 0
and 1
) in average. Conclusion should be that the example isn't a snippet
.
We measure the distance of our example with every example in the dataset using Euclidean Distance formula for multidimensional space:
distances = [] vector_array.each_with_index do |comparison_vector, vector_index| distances << Train.euclidean_distance(comparison_vector, weighted_example) end
We take the indexes of the minimum distances (k many times):
indexes = [] k.times do index = distances.index(distances.min) indexes << index distances[index] = 1000000000 end
Then, we take the real identities of each of these vectors:
predictions = [] indexes.each do |index| predictions << key_array[index].first.to_i end
key_array
here is the array containing 0
, or 1
in first item of each row, and the string in second. To give an example:
[ ... ["0", "https://www.coffeebean.com"], ["1", "Born and brewed in Southern California since 1963, The Coffee Bean & Tea Leaf is passionate about connecting loyal customers with carefully handcrafted ..."], ["0", "4"], ...]
1
represents that the item is snippet, 0
represents it isn't.
Let's return the predictions:
prediction = (predictions.sum/predictions.size).to_f if prediction < 0.5 puts "False - Item is not Snippet" return 0 else puts "True - Item is Snippet" return 1 end
Here's the full method for it:
def test example, k, vector_array, key_array example_vector = Database.word_to_tensor example example_vector.map! {|el| el = el.nil? ? 0: el} example_vector = Train.extend_vector example_vector weighted_example = Train.product example_vector distances = [] vector_array.each_with_index do |comparison_vector, vector_index| distances << Train.euclidean_distance(comparison_vector, weighted_example) end indexes = [] k.times do index = distances.index(distances.min) indexes << index distances[index] = 1000000000 end predictions = [] indexes.each do |index| predictions << key_array[index].first.to_i end puts "Predictions: #{predictions}" prediction = (predictions.sum/predictions.size).to_f if prediction < 0.5 puts "False - Item is not Snippet" return 0 else puts "True - Item is Snippet" return 1 endend
Testing with Google Organic Results for Snippet
Now that we have a function for testing, let's separate snippets from non-snippets in our examples:
true_examples = key_array.map {|el| el = el.first == "1" ? el.second : nil}.compactfalse_examples = key_array.map {|el| el = el.first == "0" ? el.second : nil}.compact
This will allow us to calculate easier.
Let's declare an empty array to collect predictions, and start with non-snippets:
predictions = []false_examples.each do |example| prediction = test example, 2, vector_array, key_array predictions << predictionendpredictions.map! {|el| el = el == 1 ? 0 : 1}
Since we know that none of these examples are snippet
, any prediction that gives 1
will be wrong. So if we test our model with false examples, and then reverse 1
s to 0
s, and 0
s to 1
s, we can combine it with our true examples:
true_examples.each do |example| prediction = test example, 2, vector_array, key_array predictions << predictionend
Now that we have the desired array filled:
prediction_train_accuracy = predictions.sum.to_f / predictions.size.to_fputs "Prediction Accuracy for Training Set is: #{prediction_train_accuracy}"
If we divide the number of 1
s to number of predictions, we can calculate the accuracy results.
Preliminary Results
We have done exactly the same process for the data we mentioned earlier. The number of predictions for snippet was 1065
, and the k
value was 2
, and the n-gram
value was 2
.
The model predicted 872
times correctly. This means the training accuracy was 0.8187793427230047
(%81.87
).
This is a good number to start, and with more tweaks, and testing with a bigger dataset, the initial hypothesis could be proven to be true.
Full Code
class Database def initialize json_data, vocab = { "<unk>" => 0, "<pad>" => 1 } super() @@pattern_data = [] @@vocab = vocab end ## Related to creating main database def self.add_new_data_to_database json_data, csv_path = nil json_data.each do |result| recursive_hash_pattern result, "" end @@pattern_data = @@pattern_data.reject { |pattern| pattern.include? nil }.uniq.compact path = "#{csv_path}master_database.csv" File.write(path, @@pattern_data.map(&:to_csv).join) end def self.element_pattern result, pattern @@pattern_data.append([result, pattern].flatten) end def self.element_array_pattern result, pattern result.each do |element| element_pattern element, pattern end end def self.assign hash, key, pattern if hash[key].is_a?(Hash) if pattern.present? pattern = "#{pattern}__#{key}" else pattern = "#{key}" end recursive_hash_pattern hash[key], pattern elsif hash[key].present? && hash[key].is_a?(Array) && hash[key].first.is_a?(Hash) if pattern.present? pattern = "#{pattern}__#{key}__n" else pattern = "#{key}" end hash[key].each do |hash_inside_array| recursive_hash_pattern hash_inside_array, pattern end elsif hash[key].present? && hash[key].is_a?(Array) if pattern.present? pattern = "#{pattern}__n" else pattern = "#{key}" end element_array_pattern hash[key], pattern else if pattern.present? pattern = "#{pattern}__#{key}" else pattern = "#{key}" end element_pattern hash[key], pattern end end def self.recursive_hash_pattern hash, pattern hash.keys.each do |key| assign hash, key, pattern end end ## Related to tokenizing def self.default_dictionary_hash { /\"/ => "", /\'/ => " \' ", /\./ => " . ", /,/ => ", ", /\!/ => " ! ", /\?/ => " ? ", /\;/ => " ", /\:/ => " ", /\(/ => " ( ", /\)/ => " ) ", /\// => " / ", /\s+/ => " ", /<br \/>/ => " , ", /http/ => "http", /https/ => " https ", } end def self.tokenizer word, dictionary_hash = default_dictionary_hash word = word.downcase dictionary_hash.keys.each do |key| word.sub!(key, dictionary_hash[key]) end word.split end def self.iterate_ngrams token_list, ngrams = 2 token_list.each do |token| 1.upto(ngrams) do |n| permutations = (token_list.size - n + 1).times.map { |i| token_list[i...(i + n)] } permutations.each do |perm| key = perm.join(" ") unless @@vocab.keys.include? key @@vocab[key] = @@vocab.size end end end end end def self.word_to_tensor word token_list = tokenizer word token_list.map {|token| @@vocab[token]} end ## Related to creating key-specific databases def self.create_key_specific_databases result_type = "organic_results", csv_path = nil, dictionary = nil, ngrams = nil, vocab_path = nil keys, examples = create_keys_and_examples keys.each do |key| specific_pattern_data = [] @@pattern_data.each_with_index do |pattern, index| word = pattern.first.to_s next if word.blank? if dictionary.present? token_list = tokenizer word, dictionary else token_list = tokenizer word end if ngrams.present? iterate_ngrams token_list, ngrams else iterate_ngrams token_list end if key == pattern.second specific_pattern_data << [ 1, word ] elsif (examples[key].to_s.to_i == examples[key]) && word.to_i == word next elsif (examples[key].to_s.to_i == examples[key]) && word.numeric? specific_pattern_data << [ 0, word ] elsif examples[key].numeric? && word.numeric? next elsif key.split("__").last == pattern.second.to_s.split("__").last specific_pattern_data << [ 1, word ] else specific_pattern_data << [ 0, word ] end end path = "#{csv_path}#{result_type}__#{key}.csv" File.write(path, specific_pattern_data.map(&:to_csv).join) end if vocab_path.present? save_vocab vocab_path else save_vocab end end def self.create_keys_and_examples keys = @@pattern_data.map { |pattern| pattern.second }.uniq examples = {} keys.each do |key| examples[key] = @@pattern_data.find { |pattern| pattern.first.to_s if pattern.second == key } end [keys, examples] end def self.numeric? return true if self =~ /\A\d+\Z/ true if Float(self) rescue false end def self.save_vocab vocab_path = "" path = "#{vocab_path}vocab.json" vocab = JSON.parse(@@vocab.to_json) File.write(path, JSON.pretty_generate(vocab)) end def self.read_vocab vocab_path vocab = File.read vocab_path @@vocab = JSON.parse(vocab) end def self.return_vocab @@vocab endendclass Train def initialize csv_path @@csv_path = csv_path @@vector_arr = [] @@word_arr = [] @@maximum_word_size = 100 @@weights = Vector[] @@losses = [] end def self.read @@word_arr = CSV.read(@@csv_path) @@word_arr end def self.define_training_set vectors @@vector_arr = vectors end def self.auto_define_maximum_size @@maximum_word_size = @@vector_arr.map {|el| el.size}.max end def self.extend_vector vector vector_arr = vector.to_a (@@maximum_word_size - vector.size).times { vector_arr << 1 } Vector.[](*vector_arr) end def self.extend_vectors @@vector_arr.each_with_index do |vector, index| @@vector_arr[index] = extend_vector vector end end def self.initialize_weights weights = [] @@maximum_word_size.times { weights << 1.0 } @@weights = Vector.[](*weights) end def self.config k = 1, lr = 0.001 [k, lr] end def self.product vector @@weights.each_with_index do |weight, index| vector[index] = weight * vector[index] end vector end def self.euclidean_distance vector_1, vector_2 subtractions = (vector_1 - vector_2).to_a subtractions.map! {|sub| sub = sub*sub } Math.sqrt(subtractions.sum) end def self.k_neighbors distances, k indexes = [] (k).times do min = distances.index(distances.min) indexes << min distances[min] = distances.max + 1 end indexes end def self.make_prediction indexes predictions = [] indexes.each do |index| predictions << @@word_arr[index][0].to_i end predictions.sum/predictions.size end def self.update_weights result, indexes, vector, lr indexes.each do |index| subtractions = @@vector_arr[index] - vector subtractions.each_with_index do |sub, sub_index| if result == 0 && sub >= 0 @@weights[sub_index] = @@weights[sub_index] + lr elsif result == 0 && sub < 0 @@weights[sub_index] = @@weights[sub_index] - lr elsif result == 1 && sub >= 0 @@weights[sub_index] = @@weights[sub_index] - lr elsif result == 1 && sub < 0 @@weights[sub_index] = @@weights[sub_index] + lr end end end end def self.mean_absolute_error real, indexes errors = [] indexes.each do |index| errors << (@@word_arr[index][0].to_i - real).abs end (errors.sum/errors.size).to_f end def self.train vector, index k, lr = config vector = extend_vector vector vector = product vector distances = [] @@vector_arr.each_with_index do |comparison_vector, vector_index| if vector_index == index distances << 100000000 else distances << euclidean_distance(comparison_vector, vector) end end indexes = k_neighbors distances, k real = @@word_arr[index][0].to_i prob_prediction = make_prediction indexes prediction = prob_prediction > 0.5 ? 1 : 0 result = real == prediction ? 1 : 0 update_weights result, indexes, vector, lr loss = mean_absolute_error real, indexes @@losses << loss puts "Result : #{real}, Prediction: #{prediction}" puts "Loss: #{loss}" prediction endendjson_path = "organic_results/example.json"json_data = File.read(json_path)json_data = JSON.parse(json_data)Database.new json_data## For training from scratch Database.add_new_data_to_database json_data, csv_path = "organic_results/"Database.create_key_specific_databases result_type = "organic_results", csv_path = "organic_results/"##Database.read_vocab "vocab.json"## We will use an iteration of csvs within a specific path in the endcsv_path = "organic_results/organic_results__snippet.csv"Train.new csv_pathkey_array = Train.readvector_array = key_array.map { |word| Database.word_to_tensor word[1] }Train.define_training_set vector_arrayTrain.auto_define_maximum_sizeTrain.extend_vectorsTrain.initialize_weightsTrain.config k = 2vector_array.each_with_index do |vector, index| Train.train vector, indexenddef test example, k, vector_array, key_array example_vector = Database.word_to_tensor example example_vector.map! {|el| el = el.nil? ? 0: el} example_vector = Train.extend_vector example_vector weighted_example = Train.product example_vector distances = [] vector_array.each_with_index do |comparison_vector, vector_index| distances << Train.euclidean_distance(comparison_vector, weighted_example) end indexes = [] k.times do index = distances.index(distances.min) indexes << index distances[index] = 1000000000 end predictions = [] indexes.each do |index| predictions << key_array[index].first.to_i end puts "Predictions: #{predictions}" prediction = (predictions.sum/predictions.size).to_f if prediction < 0.5 puts "False - Item is not Snippet" return 0 else puts "True - Item is Snippet" return 1 endendtrue_examples = key_array.map {|el| el = el.first == "1" ? el.second : nil}.compactfalse_examples = key_array.map {|el| el = el.first == "0" ? el.second : nil}.compactpredictions = []false_examples.each do |example| prediction = test example, 2, vector_array, key_array predictions << predictionendpredictions.map! {|el| el = el == 1 ? 0 : 1}true_examples.each do |example| prediction = test example, 2, vector_array, key_array predictions << predictionendprediction_train_accuracy = predictions.sum.to_f / predictions.size.to_fputs "Prediction Accuracy for Training Set is: #{prediction_train_accuracy}"
Conclusion
I'd like to apologize the reader for being one day late on the blog post. Two weeks later, we will showcase how to store them for implementation, and further tweaks to improve accuracy.
The end aim of this project is to create an open-source gem
to be implemented by everyone using a JSON Data Structure in their code.
I'd like to thank the reader for their attention, and the brilliant people of SerpApi creating wonders even in times of hardship, and for all their support.
Original Link: https://dev.to/serpapi/investigating-machine-learning-techniques-to-improve-spec-tests-iv-15cg
Dev To
An online community for sharing and discovering great ideas, having debates, and making friendsMore About this Source Visit Dev To