def test_chaining_start(self): """Test chaining start with constructor """ spinner = HaloNotebook().start() spinner_id = spinner.spinner_id self.assertIsNotNone(spinner_id) spinner.stop()
def add_features(input_file, output_file, force): """ Runs build features scripts to turn processed data from (../processed) into improved data (saved in ../processed as well). Parameters ---------- input_file: str Input file to be processed output_file: str Output processed file force: bool Force to process the input file """ spinner = Halo(text='Building features...', spinner='dots') clean_data = pd.read_csv(input_file) # Add lat/lon columns if force or not os.path.exists(output_file): spinner.start("Adding Latitude and Longitude columns") transformed_data = apply_nomatin(clean_data) transformed_data.to_csv(output_file, index=False) spinner.succeed("Latitude and Longitude features added!") else: spinner.start("Loading transformed file...") time.sleep(2) transformed_data = pd.read_csv(output_file) spinner.stop_and_persist(text="Transformed file already exists!") # Combine features transformed_data = combine_features(transformed_data) transformed_data.to_csv(output_file, index=False) return transformed_data
def anonymize(self, columns_to_exclude=[]): """ Anonymize the dataframe in a manner that leaves all pre-learning and post-learning analyses (including data valuation, variable selection, model-driven improvability, data-driven improvability and model explanation) invariant. Any transformation on continuous variables that preserves ranks will not change our pre-learning and post-learning analyses. The same holds for any 1-to-1 transformation on categorical variables. This implementation replaces ordinal values (i.e. any column that can be cast as a float) with their within-column Gaussian score. For each non-ordinal column, we form the set of all possible values, we assign a unique integer index to each value in the set, and we systematically replace said value appearing in the dataframe by the hexadecimal code of its associated integer index. For regression problems, accurate estimation of RMSE related metrics require the target column (and the prediction column for post-learning analyses) not to be anonymized. Parameters ---------- columns_to_exclude: list (optional) List of columns not to anonymize (e.g. target and prediction columns for regression problems). Returns ------- result : pandas.DataFrame The result is a pandas.Dataframe with columns (where applicable): """ spinner = Halo(text='Preparing data upload', spinner='dots') spinner.start() df = self._obj.copy() for col in df.columns: if col in columns_to_exclude: continue if df.kxy.is_categorical(col) or df[col].dtype.name == 'category': # Note: By using 'category' as dtype you are implicitly telling us that the 'natural' # order of values does not matter. unique_values = list(sorted(set(list(df[col].values)))) mapping = { unique_values[i]: "0x{:03x}".format(i) for i in range(len(unique_values)) } df[col] = df[col].apply(lambda x: mapping.get(x)) else: # Note: Any monotonic transformation applied to any continuous column would work. # The gaussian scoring below makes no assumption on marginals whatsoever. x = df[col].values.astype(float) x = x - np.nanmean(x) s = np.nanstd(x) if s > 0.0: x = x / s x = norm.cdf(x) df[col] = np.around(x.copy(), 3) spinner.succeed() return df
def test_unavailable_spinner_defaults(self): """Test unavailable spinner defaults. """ spinner = HaloNotebook('dot') self.assertEqual(spinner.text, 'dot') self.assertEqual(spinner.spinner, default_spinner)
def test_ignore_multiple_start_calls(self): """Test ignoring of multiple start calls. """ spinner = HaloNotebook() spinner.start() spinner_id = spinner.spinner_id spinner.start() self.assertEqual(spinner.spinner_id, spinner_id) spinner.stop()
def __init__(self, text): """ 초기화 Parameters ---------- text: str spinner 사용시 표시할 text """ self.spinner = Halo(text=text, spinner='dots')
def test_info(self): """Test info method """ spinner = HaloNotebook() spinner.start('foo') spinner.info() output = self._get_test_output(spinner) pattern = re.compile(r'(ℹ|¡) foo', re.UNICODE) self.assertRegexpMatches(output[-1], pattern) spinner.stop()
def test_succeed(self): """Test succeed method """ spinner = HaloNotebook() spinner.start('foo') spinner.succeed('foo') output = self._get_test_output(spinner) pattern = re.compile(r'(✔|v) foo', re.UNICODE) self.assertRegexpMatches(output[-1], pattern) spinner.stop()
def test_succeed_with_new_text(self): """Test succeed method with new text """ spinner = HaloNotebook() spinner.start('foo') spinner.succeed('bar') output = self._get_test_output(spinner)['text'] pattern = re.compile(r'(✔|v) bar', re.UNICODE) self.assertRegexpMatches(output[-1], pattern) spinner.stop()
def test_fail(self): """Test fail method """ spinner = HaloNotebook() spinner.start('foo') spinner.fail() output = self._get_test_output(spinner)['text'] pattern = re.compile(r'(✖|×) foo', re.UNICODE) self.assertRegexpMatches(output[-1], pattern) spinner.stop()
def test_if_enabled(self): """Test if spinner is enabled """ spinner = HaloNotebook(text="foo", enabled=False) spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] spinner.clear() spinner.stop() self.assertEqual(len(output), 0) self.assertEqual(output, [])
def test_warning(self): """Test warn method """ spinner = HaloNotebook() spinner.start('foo') spinner.warn('Warning!') output = self._get_test_output(spinner)['text'] pattern = re.compile(r'(⚠|!!) Warning!', re.UNICODE) self.assertRegexpMatches(output[-1], pattern) spinner.stop()
def test_context_manager(self): """Test the basic of basic spinners used through the with statement. """ with HaloNotebook(text='foo', spinner='dots') as spinner: time.sleep(1) output = self._get_test_output(spinner)['text'] self.assertEqual(output[0], '{} foo'.format(frames[0])) self.assertEqual(output[1], '{} foo'.format(frames[1])) self.assertEqual(output[2], '{} foo'.format(frames[2])) self.assertEqual(spinner.output.outputs, spinner._output(''))
class Spinner: """ Halo 라이브러리를 이용한 Spinner """ def __init__(self, text): """ 초기화 Parameters ---------- text: str spinner 사용시 표시할 text """ self.spinner = Halo(text=text, spinner='dots') def start(self): """ Spinner Start""" self.spinner.start() def stop(self): """ Spinner Stop """ self.spinner.stop()
def test_text_animation(self): """Test the text gets animated when it is too long """ text = 'This is a text that it is too long. In fact, it exceeds the eighty column standard ' \ 'terminal width, which forces the text frame renderer to add an ellipse at the end of the ' \ 'text. ' * 6 spinner = HaloNotebook(text=text, spinner='dots', animation='marquee') spinner.start() time.sleep(1) output = self._get_test_output(spinner) terminal_width = get_terminal_columns() self.assertEqual( output[0], '{0} {1}'.format(frames[0], text[:terminal_width - 2])) self.assertEqual( output[1], '{0} {1}'.format(frames[1], text[1:terminal_width - 1])) self.assertEqual(output[2], '{0} {1}'.format(frames[2], text[2:terminal_width])) spinner.succeed('End!') output = self._get_test_output(spinner) pattern = re.compile(r'(✔|v) End!', re.UNICODE) self.assertRegexpMatches(output[-1], pattern)
def test_text_ellipsing(self): """Test the text gets ellipsed if it's too long """ text = 'This is a text that it is too long. In fact, it exceeds the eighty column standard ' \ 'terminal width, which forces the text frame renderer to add an ellipse at the end of the ' \ 'text. ' * 6 spinner = HaloNotebook(text=text, spinner='dots') spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] terminal_width = get_terminal_columns() # -6 of the ' (...)' ellipsis, -2 of the spinner and space self.assertEqual(output[0], '{} {} (...)'.format(frames[0], text[:terminal_width - 6 - 2])) self.assertEqual(output[1], '{} {} (...)'.format(frames[1], text[:terminal_width - 6 - 2])) self.assertEqual(output[2], '{} {} (...)'.format(frames[2], text[:terminal_width - 6 - 2])) spinner.succeed('End!') output = self._get_test_output(spinner)['text'] pattern = re.compile(r'(✔|v) End!', re.UNICODE) self.assertRegexpMatches(output[-1], pattern)
def test_basic_spinner(self): """Test the basic of basic spinners. """ spinner = HaloNotebook(text='foo', spinner='dots') spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] spinner.stop() self.assertEqual(output[0], '{} foo'.format(frames[0])) self.assertEqual(output[1], '{} foo'.format(frames[1])) self.assertEqual(output[2], '{} foo'.format(frames[2])) self.assertEqual(spinner.output.outputs, spinner._output(''))
def test_invalid_placement(self): """Test invalid placement of spinner. """ with self.assertRaises(ValueError): HaloNotebook(placement='') HaloNotebook(placement='foo') HaloNotebook(placement=None) spinner = HaloNotebook(placement='left') with self.assertRaises(ValueError): spinner.placement = '' spinner.placement = 'foo' spinner.placement = None
def test_initial_title_spinner(self): """Test Halo with initial title. """ spinner = HaloNotebook('bar') spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] spinner.stop() self.assertEqual(output[0], '{} bar'.format(frames[0])) self.assertEqual(output[1], '{} bar'.format(frames[1])) self.assertEqual(output[2], '{} bar'.format(frames[2])) self.assertEqual(spinner.output.outputs, spinner._output(''))
def test_right_placement(self): """Test right placement of spinner. """ spinner = HaloNotebook(text="foo", placement="right") spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] (text, _) = output[-1].split(" ") self.assertEqual(text, "foo") spinner.succeed() output = self._get_test_output(spinner)['text'] (text, symbol) = output[-1].split(" ") pattern = re.compile(r"(✔|v)", re.UNICODE) self.assertEqual(text, "foo") self.assertRegexpMatches(symbol, pattern) spinner.stop()
def test_spinner_color(self): """Test ANSI escape characters are present """ for color, color_int in COLORS.items(): spinner = HaloNotebook(color=color) spinner.start() output = self._get_test_output(spinner, no_ansi=False) spinner.stop() output_merged = [arr for c in output['colors'] for arr in c] self.assertEquals(str(color_int) in output_merged, True)
def test_text_stripping(self): """Test the text being stripped before output. """ spinner = HaloNotebook(text='foo\n', spinner='dots') spinner.start() time.sleep(1) output = self._get_test_output(spinner)['text'] self.assertEqual(output[0], '{} foo'.format(frames[0])) self.assertEqual(output[1], '{} foo'.format(frames[1])) self.assertEqual(output[2], '{} foo'.format(frames[2])) spinner.succeed('foo\n') output = self._get_test_output(spinner)['text'] pattern = re.compile(r'(✔|v) foo', re.UNICODE) self.assertRegexpMatches(output[-1], pattern)
def test_text_spinner_color(self): """Test basic spinner with available colors color (both spinner and text) """ for color, color_int in COLORS.items(): spinner = HaloNotebook(text='foo', text_color=color, color=color, spinner='dots') spinner.start() time.sleep(1) output = self._get_test_output(spinner)['colors'] spinner.stop() # check if spinner colors match self.assertEqual(color_int, int(output[0][0])) self.assertEqual(color_int, int(output[1][0])) self.assertEqual(color_int, int(output[2][0])) # check if text colors match self.assertEqual(color_int, int(output[0][1])) self.assertEqual(color_int, int(output[1][1])) self.assertEqual(color_int, int(output[2][1]))
def model_explanation(data_df, prediction_column, problem_type, snr='auto', file_name=None): """ .. _model-explanation: Analyzes the variables that a model relies on the most in a brute-force fashion. The first variable is the variable the model relies on the most. The second variable is the variable that complements the first variable the most in explaining model decisions etc. Running performances should be understood as the performance achievable when trying to guess model predictions using variables with selection order smaller or equal to that of the row. When :code:`problem_type=None`, the nature of the supervised learning problem (i.e. regression or classification) is inferred from whether or not :code:`prediction_column` is categorical. Parameters ---------- data_df : pandas.DataFrame The pandas DataFrame containing the data. prediction_column : str The name of the column containing true labels. problem_type : None | 'classification' | 'regression' The type of supervised learning problem. When None, it is inferred from the column type and the number of distinct values. file_name : None | str A unique identifier characterizing data_df in the form of a file name. Do not set this unless you know why. Returns ------- result : pandas.DataFrame The result is a pandas.Dataframe with columns (where applicable): * :code:`'Selection Order'`: The order in which the associated variable was selected, starting at 1 for the most important variable. * :code:`'Variable'`: The column name corresponding to the input variable. * :code:`'Running Achievable R-Squared'`: The highest :math:`R^2` that can be achieved by a classification model using all variables selected so far, including this one. * :code:`'Running Achievable Accuracy'`: The highest classification accuracy that can be achieved by a classification model using all variables selected so far, including this one. * :code:`'Running Achievable RMSE'`: The highest classification accuracy that can be achieved by a classification model using all variables selected so far, including this one. .. admonition:: Theoretical Foundation Section :ref:`a) Model Explanation`. """ assert prediction_column in data_df.columns, 'The label column should be a column of the dataframe.' assert problem_type.lower() in ['classification', 'regression'] if problem_type.lower() == 'regression': assert np.can_cast(data_df[prediction_column], float), 'The prediction column should be numeric' k = 0 kp = 0 max_k = 100 file_name = upload_data(data_df, file_name=file_name) spinner = Halo(text='Waiting for results from the backend.', spinner='dots') spinner.start() if file_name: job_id = EXPLANATION_JOB_IDS.get( (file_name, prediction_column, problem_type), None) if job_id: api_response = APIClient.route( path='/wk/variable-selection', method='POST', \ file_name=file_name, target_column=prediction_column, \ problem_type=problem_type, timestamp=int(time()), job_id=job_id, \ snr=snr) else: api_response = APIClient.route( path='/wk/variable-selection', method='POST', \ file_name=file_name, target_column=prediction_column, \ problem_type=problem_type, timestamp=int(time()), snr=snr) initial_time = time() while api_response.status_code == requests.codes.ok and k < max_k: if kp % 2 != 0: sleep(2 if kp < 5 else 10 if k < max_k - 4 else 300) kp += 1 k = kp // 2 else: try: response = api_response.json() if 'job_id' in response: job_id = response['job_id'] EXPLANATION_JOB_IDS[(file_name, prediction_column, problem_type)] = job_id sleep(2 if kp < 5 else 10 if k < max_k - 4 else 300) kp += 1 k = kp // 2 # Note: it is important to pass the job_id to avoid being charged twice for the work. api_response = APIClient.route( path='/wk/variable-selection', method='POST', \ file_name=file_name, target_column=prediction_column, \ problem_type=problem_type, timestamp=int(time()), job_id=job_id, \ snr=snr) try: response = api_response.json() if 'eta' in response: progress_text = '%s%% Completed.' % response[ 'progress_pct'] if 'progress_pct' in response else '' spinner.text = 'Waiting for results from the backend. ETA: %s. %s' % ( response['eta'], progress_text) except: pass if ('job_id' not in response) or ('selection_order' in response): duration = int(time() - initial_time) duration = str( duration) + 's' if duration < 60 else str( duration // 60) + 'min' result = {} if 'selection_order' in response: result['Selection Order'] = response[ 'selection_order'] if 'variable' in response: result['Variable'] = response['variable'] if 'r-squared' in response: result['Running Achievable R-Squared'] = response[ 'r-squared'] if 'log-likelihood' in response: result[ 'Running Achievable Log-Likelihood Per Sample'] = response[ 'log-likelihood'] if 'rmse' in response and problem_type.lower( ) == 'regression': result['Running Achievable RMSE'] = response[ 'rmse'] if 'accuracy' in response and problem_type.lower( ) == 'classification': result['Running Achievable Accuracy'] = response[ 'accuracy'] result = pd.DataFrame.from_dict(result) if 'selection_order' in response: result.set_index('Selection Order', inplace=True) spinner.text = 'Received results from the backend after %s.' % duration spinner.succeed() return result except: logging.exception( '\nModel explanation failed. Last HTTP code: %s, Content: %s' % (api_response.status_code, api_response.content)) spinner.text = 'The backend encountered an unexpected error we are looking into. Please try again later.' spinner.fail() return None if api_response.status_code != requests.codes.ok: spinner.text = 'The backend is taking longer than expected. Please try again later' spinner.fail() try: response = api_response.json() if 'message' in response: logging.error('\n%s' % response['message']) except: logging.error( '\nModel explanation failed. Last HTTP code: %s, Content: %s' % (api_response.status_code, api_response.content)) raise LongerThanExpectedException( 'The backend is taking longer than expected, but rest reassured your task is still running. Please try again later to retrieve your results.' ) return None
def test_default_placement(self): """Test default placement of spinner. """ spinner = HaloNotebook() self.assertEqual(spinner.placement, 'left')
def process_dataset(input_file, output_file, scrape): """ Runs data processing scripts to turn raw data from (../raw) into cleaned data ready to be analyzed (saved in ../processed). Parameters ---------- input_file: str Input file to be processed output_file: str Output processed file scrape: bool Force the scraping process """ spinner = Halo(text='Making dataset...', spinner='dots') logger = logging.getLogger(__name__) logger.info('Making final dataset from raw data') # Scrape data if scrape or not os.path.exists(input_file): spinner.start("Scraping data") with open('./references/urls.txt', 'r') as f: urls = f.readlines() scraped_dfs = [] for url in urls: scraped_dfs.append(navigate(url, 1, 500)) # Save results raw_data = pd.concat(scraped_dfs) raw_data.to_csv(input_file, index=False) spinner.succeed("Data Scrapped!") else: spinner.succeed("Loading scraped file...") raw_data = pd.read_csv(input_file) spinner.succeed("Scraped file already exists!") # Remove duplicates spinner.start("Removing duplicates and invalid values...") time.sleep(1) interim_data = remove_duplicates_and_na(raw_data) interim_data.to_csv(output_file.replace("processed", "interim"), index=False) spinner.succeed("Done removing duplicates!") # Remove outliers spinner.start("Removing outliers and inconsistent values...") time.sleep(1) final_data = remove_outliers(interim_data) final_data.to_csv(output_file, index=False) spinner.succeed("Done removing outliers!") spinner.start("Cleaning processing done!") spinner.stop_and_persist(symbol='✔'.encode('utf-8'), text="Cleaning processing done!") return final_data
def data_valuation(data_df, target_column, problem_type, snr='auto', include_mutual_information=False, file_name=None): """ .. _data-valuation: Estimate the highest performance metrics achievable when predicting the :code:`target_column` using all other columns. When :code:`problem_type=None`, the nature of the supervised learning problem (i.e. regression or classification) is inferred from whether or not :code:`target_column` is categorical. Parameters ---------- data_df : pandas.DataFrame The pandas DataFrame containing the data. target_column : str The name of the column containing true labels. problem_type : None | 'classification' | 'regression' The type of supervised learning problem. When None, it is inferred from the column type and the number of distinct values. include_mutual_information : bool Whether to include the mutual information between target and explanatory variables in the result. file_name : None | str A unique identifier characterizing data_df in the form of a file name. Do not set this unless you know why. Returns ------- achievable_performance : pandas.Dataframe The result is a pandas.Dataframe with columns (where applicable): * :code:`'Achievable Accuracy'`: The highest classification accuracy that can be achieved by a model using provided inputs to predict the label. * :code:`'Achievable R-Squared'`: The highest :math:`R^2` that can be achieved by a model using provided inputs to predict the label. * :code:`'Achievable RMSE'`: The lowest Root Mean Square Error that can be achieved by a model using provided inputs to predict the label. * :code:`'Achievable Log-Likelihood Per Sample'`: The highest true log-likelihood per sample that can be achieved by a model using provided inputs to predict the label. .. admonition:: Theoretical Foundation Section :ref:`1 - Achievable Performance`. """ assert target_column in data_df.columns, 'The label column should be a column of the dataframe.' assert problem_type.lower() in ['classification', 'regression'] if problem_type.lower() == 'regression': assert np.can_cast(data_df[target_column], float), 'The target column should be numeric' k = 0 max_k = 100 file_name = upload_data(data_df, file_name=file_name) spinner = Halo(text='Waiting for results from the backend.', spinner='dots') spinner.start() if file_name: job_id = VALUATION_JOB_IDS.get( (file_name, target_column, problem_type, snr), None) if job_id: api_response = APIClient.route( path='/wk/data-valuation', method='POST', file_name=file_name, target_column=target_column, \ problem_type=problem_type, \ timestamp=int(time()), job_id=job_id, \ snr=snr) else: api_response = APIClient.route( path='/wk/data-valuation', method='POST', \ file_name=file_name, target_column=target_column, \ problem_type=problem_type, timestamp=int(time()), \ snr=snr) initial_time = time() while api_response.status_code == requests.codes.ok and k < max_k: try: response = api_response.json() if 'eta' in response: progress_text = '%s%% Completed.' % response[ 'progress_pct'] if 'progress_pct' in response else '' spinner.text = 'Waiting for results from the backend. ETA: %s. %s' % ( response['eta'], progress_text) if ('job_id' in response) and ('r-squared' not in response): job_id = response['job_id'] VALUATION_JOB_IDS[(file_name, target_column, problem_type, snr)] = job_id k += 1 sleep(15.) # Note: it is important to pass the job_id to avoid being charged twice for the same work. api_response = APIClient.route( path='/wk/data-valuation', method='POST', file_name=file_name, target_column=target_column, \ problem_type=problem_type, \ timestamp=int(time()), job_id=job_id, \ snr=snr) try: response = api_response.json() if 'eta' in response: progress_text = '%s%% Completed.' % response[ 'progress_pct'] if 'progress_pct' in response else '' spinner.text = 'Waiting for results from the backend. ETA: %s. %s' % ( response['eta'], progress_text) except: pass if ('job_id' not in response) or ('r-squared' in response): duration = int(time() - initial_time) duration = str(duration) + 's' if duration < 60 else str( duration // 60) + 'min' result = {} if 'r-squared' in response: result['Achievable R-Squared'] = [ response['r-squared'] ] if 'log-likelihood' in response: result['Achievable Log-Likelihood Per Sample'] = [ response['log-likelihood'] ] if 'rmse' in response and problem_type.lower( ) == 'regression': result['Achievable RMSE'] = [response['rmse']] if 'accuracy' in response and problem_type.lower( ) == 'classification': result['Achievable Accuracy'] = [response['accuracy']] if include_mutual_information and 'mi' in response: result['Mutual Information'] = [response['mi']] result = pd.DataFrame.from_dict(result) spinner.text = 'Received results from the backend after %s.' % duration spinner.succeed() return result except: logging.exception( '\nData valuation failed. Last HTTP code: %s' % api_response.status_code) spinner.text = 'The backend encountered an unexpected error we are looking into. Please try again later.' spinner.fail() return None if api_response.status_code != requests.codes.ok: spinner.text = 'The backend is taking longer than expected. Try again later.' spinner.fail() try: response = api_response.json() if 'message' in response: logging.error('\n%s' % response['message']) except: logging.error('\nData valuation failed. Last HTTP code: %s' % api_response.status_code) raise LongerThanExpectedException( 'The backend is taking longer than expected, but rest reassured your task is still running. Please try again later to retrieve your results.' ) return None
def test_spinner_getters_setters(self): """Test spinner getters and setters. """ spinner = HaloNotebook() self.assertEqual(spinner.text, '') self.assertEqual(spinner.color, 'cyan') self.assertIsNone(spinner.spinner_id) spinner.spinner = 'dots12' spinner.text = 'bar' spinner.color = 'red' self.assertEqual(spinner.text, 'bar') self.assertEqual(spinner.color, 'red') if is_supported(): self.assertEqual(spinner.spinner, Spinners['dots12'].value) else: self.assertEqual(spinner.spinner, default_spinner) spinner.spinner = 'dots11' if is_supported(): self.assertEqual(spinner.spinner, Spinners['dots11'].value) else: self.assertEqual(spinner.spinner, default_spinner) spinner.spinner = 'foo_bar' self.assertEqual(spinner.spinner, default_spinner) # Color is None spinner.color = None spinner.start() spinner.stop() self.assertIsNone(spinner.color)
def test_id_not_created_before_start(self): """Test Spinner ID not created before start. """ spinner = HaloNotebook() self.assertEqual(spinner.spinner_id, None)
def data_driven_improvability(data_df, target_column, new_variables, problem_type, snr='auto', file_name=None): """ .. data-driven-improvability: Estimate the potential performance boost that a set of new explanatory variables can bring about. Parameters ---------- data_df : pandas.DataFrame The pandas DataFrame containing the data. target_column : str The name of the column containing true labels. new_variables : list The names of the columns to use as new explanatory variables. problem_type : None | 'classification' | 'regression' The type of supervised learning problem. When None, it is inferred from whether or not :code:`target_column` is categorical. file_name : None | str A unique identifier characterizing data_df in the form of a file name. Do not set this unless you know why. Returns ------- result : pandas.Dataframe The result is a pandas.Dataframe with columns (where applicable): * :code:`'Accuracy Boost'`: The classification accuracy boost that the new explanatory variables can bring about. * :code:`'R-Squared Boost'`: The :math:`R^2` boost that the new explanatory variables can bring about. * :code:`'RMSE Reduction'`: The reduction in Root Mean Square Error that the new explanatory variables can bring about. * :code:`'Log-Likelihood Per Sample Boost'`: The boost in log-likelihood per sample that the new explanatory variables can bring about. .. admonition:: Theoretical Foundation Section :ref:`3 - Model Improvability`. """ assert target_column in data_df.columns, 'The label column should be a column of the dataframe.' assert problem_type.lower() in ['classification', 'regression'] assert len(new_variables) > 0, 'New variables should be provided' for col in new_variables: assert col in data_df.columns, '%s should be a column in the dataframe' % col if problem_type.lower() == 'regression': assert np.can_cast(data_df[target_column], float), 'The target column should be numeric' k = 0 kp = 0 max_k = 100 file_name = upload_data(data_df, file_name=file_name) spinner = Halo(text='Waiting for results from the backend.', spinner='dots') spinner.start() if file_name: job_id = DD_IMPROVABILITY_JOB_IDS.get((file_name, target_column, str(new_variables), problem_type, snr), None) if job_id: api_response = APIClient.route( path='/wk/data-driven-improvability', method='POST', \ file_name=file_name, target_column=target_column, \ problem_type=problem_type, new_variables=json.dumps(new_variables), \ job_id=job_id, timestamp=int(time()), snr=snr) else: api_response = APIClient.route( path='/wk/data-driven-improvability', method='POST', \ file_name=file_name, target_column=target_column, \ problem_type=problem_type, new_variables=json.dumps(new_variables), \ timestamp=int(time()), snr=snr) initial_time = time() while api_response.status_code == requests.codes.ok and k < max_k: if kp%2 != 0: sleep(2 if kp<5 else 10 if k < max_k-4 else 300) kp += 1 k = kp//2 else: try: response = api_response.json() if 'job_id' in response: job_id = response['job_id'] DD_IMPROVABILITY_JOB_IDS[(file_name, target_column, str(new_variables), problem_type, snr)] = job_id sleep(2 if kp<5 else 10 if k < max_k-4 else 300) kp += 1 k = kp//2 api_response = APIClient.route( path='/wk/data-driven-improvability', method='POST', \ file_name=file_name, target_column=target_column, \ problem_type=problem_type, new_variables=json.dumps(new_variables), \ timestamp=int(time()), snr=snr) try: response = api_response.json() if 'eta' in response: progress_text = '%s%% Completed.' % response['progress_pct'] if 'progress_pct' in response else '' spinner.text = 'Waiting for results from the backend. ETA: %s. %s' % (response['eta'], progress_text) except: pass if ('job_id' not in response) or ('r-squared-boost' in response): duration = int(time()-initial_time) duration = str(duration) + 's' if duration < 60 else str(duration//60) + 'min' result = {} if 'r-squared-boost' in response: result['R-Squared Boost'] = [response['r-squared-boost']] if 'log-likelihood-boost' in response: result['Log-Likelihood Per Sample Boost'] = [response['log-likelihood-boost']] if 'rmse-reduction' in response and problem_type.lower() == 'regression': result['RMSE Reduction'] = [response['rmse-reduction']] if 'accuracy-boost' in response and problem_type.lower() == 'classification': result['Accuracy Boost'] = [response['accuracy-boost']] result = pd.DataFrame.from_dict(result) spinner.text = 'Received results from the backend after %s' % duration spinner.succeed() return result except: spinner.text = 'The backend encountered an unexpected error we are looking into. Please try again later.' spinner.fail() return None if api_response.status_code != requests.codes.ok: spinner.text = 'The backend is taking longer than expected. Try again later.' spinner.fail() try: response = api_response.json() if 'message' in response: logging.error('\n%s' % response['message']) except: logging.error('\nData-driven improvability failed. Last HTTP code: %s' % api_response.status_code) return None