def test_word_existence_counts_per_word(df):
try:
df_fever = verbal_autopsy_functions.counts_per_word(
df, 'word_nonexisting')
except KeyError:
print('Non-existing word causes an error.')
def test_type_counts_per_word_output(df):
df_fever = verbal_autopsy_functions.counts_per_word(df, 'word_fever')
if type(df_fever) is not pd.core.frame.DataFrame:
print('The output of the type is not a data frame.')
def test_columns_counts_per_word_output(df):
df_fever = verbal_autopsy_functions.counts_per_word(df, 'word_fever')
if list(df_fever.columns.values) != [
'site', 'Cause of death', 'Times word_fever is mentioned.'
]:
print('The column names are not as expected.')
# -------------------------------------------
# Loading the verbal autopsy analysis module
# -------------------------------------------
import verbal_autopsy_functions
import imp
imp.reload(verbal_autopsy_functions)
# -------------------------------------------
# Reading the data
# -------------------------------------------
# creating the data path
data_path = os.path.join(os.getcwd(), '..', 'data')
# reading the data files
df = pd.read_csv(os.path.join(data_path,
'IHME_PHMRC_VA_DATA_ADULT_Y2013M09D11_0.csv'),
low_memory=False)
cb = pd.read_excel(
os.path.join(data_path, 'IHME_PHMRC_VA_DATA_CODEBOOK_Y2013M09D11_0.xlsx'))
# creating the results path
results_path = os.path.join(os.getcwd(), '..', 'results')
# calclulate the counts table for each word and write it to a csv file
for word in ['word_asthma', 'word_fever', 'word_cough']:
table_counts = verbal_autopsy_functions.counts_per_word(df, word)
table_counts.to_csv(os.path.join(results_path, word + '.csv'))
# ------------------------------------------- import verbal_autopsy_functions import imp imp.reload(verbal_autopsy_functions) # ------------------------------------------- # Reading the data # ------------------------------------------- # creating the data path data_path = os.path.join(os.getcwd(),'..','data') # reading the data files df = pd.read_csv(os.path.join(data_path,'IHME_PHMRC_VA_DATA_ADULT_Y2013M09D11_0.csv'),low_memory = False) cb = pd.read_excel(os.path.join(data_path,'IHME_PHMRC_VA_DATA_CODEBOOK_Y2013M09D11_0.xlsx')) # creating the results path results_path = os.path.join(os.getcwd(),'..','results') # calclulate the counts table for each word and write it to a csv file for word in ['word_asthma','word_fever','word_cough']: table_counts = verbal_autopsy_functions.counts_per_word(df,word) table_counts.to_csv(os.path.join(results_path,word+'.csv'))
def test_word_existence_counts_per_word(df):
try:
df_fever = verbal_autopsy_functions.counts_per_word(df,'word_nonexisting')
except KeyError:
print ('Non-existing word causes an error.')
def test_columns_counts_per_word_output(df):
df_fever = verbal_autopsy_functions.counts_per_word(df,'word_fever')
if list(df_fever.columns.values)!=['site', 'Cause of death','Times word_fever is mentioned.']:
print ('The column names are not as expected.')
def test_type_counts_per_word_output(df):
df_fever = verbal_autopsy_functions.counts_per_word(df,'word_fever')
if type(df_fever) is not pd.core.frame.DataFrame:
print ('The output of the type is not a data frame.')
