def test_load_treated(self):
data = tcu_io.load_treated_csv_to_numpy(TREATED_TCU_FILE)
self.assertEquals(29202, len(data))
names = ('Cluster', 'ChavePregao', 'UASG', 'PregoeiroOficial',
'AceitoPara_CNPJ', 'PeloMenorLance', 'ValorReferencia',
'GanhoPregao', 'SuperFaturamento')
for column_name in names:
self.assertEquals(len(data[column_name]), 29202)
def main(tcu_fpath):
data = tcu_io.load_treated_csv_to_numpy(tcu_fpath)
print(stats.pearsonr(data['ValorReferencia'], data['PeloMenorLance']))
print(stats.pearsonr(data['ValorReferencia'], data['GanhoPregao']))
print(stats.pearsonr(data['GanhoPregao'], data['PeloMenorLance']))
to_corr_cat = [('SuperFaturamento', 'PregoeiroOficial'),
('SuperFaturamento', 'AceitoPara_CNPJ'),
('SuperFaturamento', 'Cluster')]
for pair in to_corr_cat:
row = pair[0]
col = pair[1]
vals_row = set(data[row])
vals_col = set(data[col])
n_rows = len(vals_row)
n_cols = len(vals_col)
#Creating table
contingency_table = np.ndarray(shape=(n_rows, n_cols), dtype='i')
for i, possible_row in enumerate(vals_row):
for j, possible_col in enumerate(vals_col):
#Create boolean arrays with lines that contain the values
with_both = \
(data[row] == possible_row) & (data[col] == possible_col)
num_occur = with_both.sum()
contingency_table[i, j] = num_occur
print('Correlating %s', pair)
chi2, p, dof, e = contingency.chi2_contingency(contingency_table)
print('Correlation', pair, ': chi2 = %f; p = %f; df = %f;' \
%(chi2, p, dof))
