base) Jianguos-Air:code jianguolu$ python TF_lu.py Corpus size: unigram [122988] [5056] bigrams [67819] [17667] Corpus size: unigram [122988, 306057] [5056, 9719] bigrams [67819, 180682] [17667, 44607] ('software_engineering', 0.0012013042732109147) ('software_development', 0.0033003300330033004) ('international_conference', 0.005076142131979695) ('software_systems', 0.013888888888888888) ('empirical_study', 0.015384615384615385) ('experience_report', 0.016129032258064516) ('model_driven', 0.017857142857142856) ('software_product', 0.02) ('source_software', 0.021739130434782608) ('product_line', 0.023255813953488372) ('open_source', 0.02564102564102564) ('self_adaptive', 0.02702702702702703) ('neural_network', 0.02702702702702703) ('case_study', 0.028089887640449437) ('data_flow', 0.029411764705882353) ('model_based', 0.031578947368421054) ('formal_methods', 0.03333333333333333) ('system_based', 0.037037037037037035) ('process_modeling', 0.041666666666666664) ('configuration_management', 0.043478260869565216) ('cloud_computing', 0.045454545454545456) ('applications_using', 0.045454545454545456) ('e_using', 0.047619047619047616) ('program_analysis', 0.047619047619047616) ('agent_based', 0.047619047619047616) ('second_international', 0.05) ('cost_estimation', 0.05) ('time_systems', 0.05) ('web_application', 0.05) ('use_case', 0.05263157894736842) ('application_development', 0.05263157894736842) ('f_design', 0.05263157894736842) ('lessons_learned', 0.05555555555555555) ('service_oriented', 0.05555555555555555) ('method_based', 0.05555555555555555) ('driven_approach', 0.058823529411764705) ('panel_session', 0.058823529411764705) ('formal_verification', 0.058823529411764705)