v = pd.DataFrame() v['id'] = train.id v['y'] = y cv, _ = run(train, y, test, v, z) state.save('model', (v, z, cv, None)) else: v, z, cv, _ = saved return v, z, cv, _ if '__main__' == __name__: print('starting', state.now()) v, z, cv, _ = predict() state.save_model(v, z, cv) if public_score == None: # если есть public score - перезаписывать отправленное уже не стоит state.save_predicts(z) else: import os if os.path.exists('../model_scores.csv'): mdf = pd.read_csv('../model_scores.csv') else: mdf = pd.DataFrame(columns=['timestamp', 'model', 'cv', 'cv std', 'public score']) idx = mdf.model == state.base_name_ if np.sum(idx) == 0: mdf.loc[len(mdf), 'model'] = state.base_name_ idx = mdf.model == state.base_name_ if (mdf.ix[idx, 'public score'] != public_score).bool(): mdf.ix[idx, 'public score'] = public_score mdf.ix[idx, 'timestamp'] = state.now() mdf.ix[idx, 'cv'] = np.mean(cv) mdf.ix[idx, 'cv std'] = np.std(cv)
v['y'] = y cv, _ = run(train, y, test, v, z) state.save('model', (v, z, cv, None)) else: v, z, cv, _ = saved return v, z, cv, _ if '__main__' == __name__: print('starting', state.now()) v, z, cv, _ = predict() if not debug_mode: state.save_model(v, z, cv) if public_score == None: # если есть public score - перезаписывать отправленное уже не стоит state.save_predicts(z) else: import os if os.path.exists('../model_scores.csv'): mdf = pd.read_csv('../model_scores.csv') else: mdf = pd.DataFrame( columns=['timestamp', 'model', 'cv', 'cv std', 'public score']) idx = mdf.model == state.base_name_ if np.sum(idx) == 0: mdf.loc[len(mdf), 'model'] = state.base_name_ idx = mdf.model == state.base_name_ if (mdf.ix[idx, 'public score'] != public_score).bool(): mdf.ix[idx, 'public score'] = public_score mdf.ix[idx, 'timestamp'] = state.now() mdf.ix[idx, 'cv'] = np.mean(cv)