def different_dictionaries_experiment(in_text_name, in_text_handler):
for dictionary in dict_config.DICTS:
freq_dict = freq_dictionary.build_freq_dictionary(in_text_handler.sentences, dictionary)
critical_freq = text_model.calculate_critical_frequency(freq_dict)
empirical_critical_freq = critical_frequency_analysis.get_empirical_critical_frequency(freq_dict.values())
plot_filename = os.path.join('./plots_w_cr_%s' % dictionary, in_text_name + '.png')
plotting.make_plot_with_critical_frequency(plot_filename, \
in_text_handler.text_info, \
freq_dict.values(), \
critical_freq)
two_w_cr_plot_filename = os.path.join('./plots_two_w_cr_%s' % dictionary, in_text_name + '.png')
plotting.make_plot_with_two_critical_frequencies(two_w_cr_plot_filename, \
in_text_handler.text_info, \
freq_dict.values(), \
critical_freq,
empirical_critical_freq)
chart_filename = os.path.join('./charts_%s' % dictionary, in_text_name + '.txt')
write_words_chart(chart_filename, freq_dict, critical_freq)
if (dictionary == 'fs_dict'):
dominant_lexemes = [lexeme for lexeme in freq_dict if freq_dict[lexeme] > critical_freq]
GLOBAL_SENTENCES_STAT['sentence_counts'].append(int(in_text_handler.text_info['sentences']))
GLOBAL_SENTENCES_STAT['dominant_counts'].append(len(dominant_lexemes))
GLOBAL_WORDS_STAT['word_counts'].append(int(in_text_handler.text_info['words']))
GLOBAL_WORDS_STAT['dominant_counts'].append(len(dominant_lexemes))
critical_frequency_error = critical_frequency_analysis.get_critical_frequency_error(freq_dict)
GLOBAL_CRITICAL_FREQUENCY_ERROR_STAT.append(critical_frequency_error)
def empirical_critical_frequency_experiment(in_text_name, in_text_handler):
for dictionary in ['fs_dict', 'assoc_power_dict']:
freq_dict = freq_dictionary.build_freq_dictionary(in_text_handler.sentences, dictionary)
critical_freq = critical_frequency_analysis.get_empirical_critical_frequency(freq_dict.values())
chart_filename = os.path.join('./charts_empirical_%s' % dictionary, in_text_name + '.txt')
write_words_chart(chart_filename, freq_dict, critical_freq)