def load_sterilization():
df = pd.read_csv('../data/sterilization.csv',
na_filter=True,
na_values=['#DIV/0!'])
df = jn.DataFrame(df).clean_names().label_encode('treatment')
mapping = dict(zip(df['treatment'], df['treatment_enc']))
return df, mapping
def test_multiindex_clean_names_method_chain(multiindex_dataframe):
df = jn.DataFrame(multiindex_dataframe).clean_names()
levels = [['a', 'bell_chart', 'decorated_elephant'],
['b', 'normal_distribution', 'r_i_p_rhino_']]
labels = [[0, 1, 2], [0, 1, 2]]
expected_columns = pd.MultiIndex(levels=levels, labels=labels)
assert set(df.columns) == set(expected_columns)
def load_finches(path):
# Load the data
df = pd.read_csv(path)
# Data cleaning methods. This is provided for you. Follow along the annotations
# to learn what's going on.
df = (jn.DataFrame(df) # wrap dataframe in a Janitor dataframe.
.clean_names() # clean column names
.rename_column('blength', 'beak_length') # rename blength to beak_length (readability fix)
.rename_column('bdepth', 'beak_depth') # rename bdepth to beak_depth (readability fix)
.label_encode('species') # create a `species_enc` column that has the species encoded numerically
)
return df
import pandas as pd
import janitor as jn
df = pd.read_excel('dirty_data.xlsx')
df = (jn.DataFrame(df).clean_names().remove_empty().rename_column(
'%_allocated',
'percent_allocated').rename_column('full_time?', 'full_time').coalesce(
['certification', 'certification.1'],
'certification').encode_categorical(
['subject', 'employee_status',
'full_time']).convert_excel_date('hire_date'))
print(df)
def test_rename_column(dataframe):
dataframe = jn.DataFrame(dataframe).clean_names()
df = dataframe.rename_column('a', 'index')
assert set(df.columns) == set(
['index', 'bell_chart', 'decorated_elephant']) # noqa: E501
def test_get_features_targets(dataframe):
dataframe = jn.DataFrame(dataframe).clean_names()
X, y = dataframe.get_features_targets(target_columns='bell_chart')
assert X.shape == (3, 2)
assert y.shape == (3, )
def test_clean_names_method_chain(dataframe):
df = jn.DataFrame(dataframe).clean_names()
expected_columns = ['a', 'bell_chart', 'decorated_elephant']
assert set(df.columns) == set(expected_columns)
def test_fill_empty(null_df):
df = jn.DataFrame(null_df).fill_empty(columns=['2'], value=3)
assert set(df.loc[:, '2']) == set([3])
def test_convert_excel_date():
df = pd.read_excel('examples/dirty_data.xlsx')
df = jn.DataFrame(df).clean_names()
df = convert_excel_date(df, 'hire_date')
assert df['hire_date'].dtype == 'M8[ns]'
def load_kruschke():
df = pd.read_csv('../data/iq.csv', index_col=0) # comment out the path to the file for students.
df = jn.DataFrame(df).label_encode('treatment')
return df
import pandas as pd
import janitor as jn
df = pd.read_excel("dirty_data.xlsx")
df = (
jn.DataFrame(df)
.clean_names()
.remove_empty()
.rename_column("%_allocated", "percent_allocated")
.rename_column("full_time?", "full_time")
.coalesce(["certification", "certification.1"], "certification")
.encode_categorical(["subject", "employee_status", "full_time"])
.convert_excel_date("hire_date")
)
print(df)
