def test_values(self): dtype = [('iso3','|S16'),('year','<i4'),('y','<f8')] self.data = utilities.read('test_read.csv', dtype) self.assertTrue((self.data['iso3'] == ['USA','USA','USA']).all() == True) self.assertTrue((self.data['year'] == range(1970,1973)).all() == True) self.assertTrue((self.data['y'][0:2] == [0,1]).all() == True) # test for nan self.assertTrue((self.data['y'][2] != self.data['y'][2]))
def Mon_Jasnow(sub_dir): Ns = read(sub_dir, "sizes") Ts = read(sub_dir, "temps") name = "tau_MJ" tau = read(sub_dir, name) fig, ax = plt.subplots(figsize=(6, 4)) ax.set_ylabel("$\\tau/[J]$") ax.set_xlabel("$T/[J]$") for i, N in enumerate(Ns): ax.plot(Ts, tau[i], "--.", label="$N={}$".format(int(N))) ax.plot([Tc, Tc], ax.get_ylim(), "k--", label="$T_c$") ax.legend() ax.grid(True) plt.tight_layout() plt.savefig("figs/" + sub_dir + name + ".png", dpi=300) plt.close(fig)
def evaluate_estimates(out_file, key, est_dir, est_y, gold_standard_file, y): """ Evaluate estimates stored in a directory of csvs against the gold standard. Parameters ---------- out_file : string A path to a csv in which to store summary error metrics key : list of strings A list of strings that correspond to columns in the estimates files and in the gold standard files to serve as the key in merging these files. If evaluates_estimates is being run from the command line, then key must be enclosed in double quotes (e.g. \"['iso3','year']\") est_dir : string The path to a directory with the csvs of the estimates. All csvs in this directory will be assumed to contain estimates. The path should end with a / est_y : string The name of the column in the estimate files that holds the predictions from the model y : string The name of the column in the gold standard file that holds the response variable. This should also be the name of the column in the estimates files that holds the knocked out and noised response variable. gold_standard_file : string The path to the gold standard file Notes ----- see parse_filename for a guide to the naming convention of the predicted response variables """ model_design_vars = {} data = utilities.read(gold_standard_file) data = utilities.add_unique_id(data, key, 'unique_id_for_join_by') files = os.listdir(est_dir) for file in files: file_key = parse_filename(file) path = est_dir + file new_data = utilities.read(path) # rename variable names = [] for name in new_data.dtype.names: if name == est_y: est_y_name = est_y + '_' + str(file_key['model']) + '_' + str(file_key['design']) + '_' + str(file_key['rep']) names.append(est_y_name) elif name == y: y_name = y + '_' + str(file_key['model']) + '_' + str(file_key['design']) + '_' + str(file_key['rep']) names.append(y_name) else: names.append(name) new_data.dtype.names = tuple(names) # collect up variables corresponding to a certain model and design if model_design_vars.has_key(file_key['model']) == False: model_design_vars[file_key['model']] = {} if model_design_vars[file_key['model']].has_key(file_key['design']) == False: model_design_vars[file_key['model']][file_key['design']] = [] model_design_vars[file_key['model']][file_key['design']].append(est_y_name) new_data = utilities.add_unique_id(new_data, key, 'unique_id_for_join_by') new_data = new_data[['unique_id_for_join_by', est_y_name, y_name]] # http://stackoverflow.com/questions/2774949/merging-indexed-array-in-python data = numpy.lib.recfunctions.join_by('unique_id_for_join_by', data, new_data) # this would write a file with the gold standard and all the predictions #utilities.write(out_predictions_file, data) data = numpy.lib.recfunctions.drop_fields(data, 'unique_id_for_join_by') model_design_errors = {} for model in model_design_vars.keys(): model_design_errors[model] = {} for design in model_design_vars[model].keys(): model_design_errors[model][design] = {} truth = [] obs = [] for var in model_design_vars[model][design]: y_var = var.replace(est_y, y) for i in range(0, len(data[y])): if utilities.is_nan(data[y_var][i]) == True: pdb.set_trace() truth.append(data[y][i]) obs.append(data[var][i]) truth = np.array(truth) obs = np.array(obs) model_design_errors[model][design] = {} errors = errormetrics.get_error_metrics() for error in errors: error_str = 'errormetrics.' + error + '()' error_class = eval(error_str) model_design_errors[model][design][error] = error_class.calc_error(truth, obs, True) errors = [] for model in model_design_errors.keys(): for design in model_design_errors[model].keys(): for error in model_design_errors[model][design].keys(): errors.append(error) errors = np.unique(errors) writer = csv.writer(open(out_file, 'wb')) fieldnames = ['model','design'] + errors.tolist() writer.writerow(fieldnames) for model in model_design_errors.keys(): for design in model_design_errors[model].keys(): row = [model, design] for error in errors: if model_design_errors[model][design].has_key(error) == True: row.append(model_design_errors[model][design][error]) else: row.append('') writer.writerow(row) writer = []
def simulate_data(out_dir, y, se, gold_standard_file, design_file): """ Simulate data by knocking out and adding noise to a gold standard file. How data is knocked out and how noise is added is determined by parameters specified in the design file. Parameters ---------- out_dir : string The path to a directory in which to output the noisy and knocked out data. The path should end with a / y : string The column name in the gold standard file corresponding to the response to be knocked out and noised up. se : string The column name in the gold standard file corresponding to the standard error of the response. If se == '', then a se variable will be created named 'se' and filled with 0's. If noise is added, then this se variable will be set to the standard error of the noise. gold_standard_file : string The path to a csv. design_file : string The path to a csv. If a knock out test is to be performed, there must be a column called knockerouters. If noise is to be added, there must be a column called noisers. If there is a column called rep, then each test will be repeated rep times. If no such column is provided, each test will only be run once. All other columns are parameters for the knockerouter function or the noiser function. These two functions must not not share column names for parameters. All column entries (not the header) must be enclosed in double quotes. A string will be enclosed in single quotes and then double quotes (e.g. \"'USA'\"), whereas a number or an array will be enclosed only in double quotes (e.g. \"2\", \"[1,2,3]\"). See Also -------- utilities.read """ if os.path.isdir(out_dir) == False: os.mkdir(out_dir) gold_data = utilities.read(gold_standard_file) if se == "": gold_data = numpy.lib.recfunctions.append_fields(gold_data, "se", [0] * len(gold_data), "<f4") se = "se" reader = csv.reader(open(design_file)) on_header = True index = 0 rep_index = np.nan for row in reader: if on_header == True: header = row on_header = False for i in range(0, len(header)): if header == "rep": rep_index = i else: if utilities.is_nan(rep_index) == True: reps = 1 else: reps = int(row[rep_index]) for i in range(0, reps): data = gold_data row_dict = {} for j, name in enumerate(header): row_j = eval(row[j]) row_dict[name] = row_j for func_collection in ["knockerouters", "noisers", "biasers"]: if row_dict.has_key(func_collection) == True: fun_str = func_collection + "." + row_dict[func_collection] if func_collection == "biasers": fun_str = fun_str + "(data, y" else: fun_str = fun_str + "(data, y, se" get_args_str = "inspect.getargspec(" + func_collection + "." + row_dict[func_collection] + ")" args = eval(get_args_str)[0] for arg in args: if (arg in ["data", "y", "se"]) == False: fun_str = fun_str + ", row_dict['" + arg + "']" fun_str = fun_str + ")" data = eval(fun_str) gold_standard_file = gold_standard_file.split("/") gold_standard_file = gold_standard_file[len(gold_standard_file) - 1] new_file = ( out_dir + "sim_" + gold_standard_file.replace(".csv", "") + "_" + str(index) + "_" + str(i) + ".csv" ) utilities.write(new_file, data) index = index + 1