def test_grouped_mutate_repeated_keys():
df = mtcars.copy()
df.index = list(range(16)) + list(range(16))
with pytest.raises(ValueError): # cannot reindex from duplicate axis
with dppd(df) as (ddf, X):
ddf.groupby("cyl").mutate(grp_rank={
grp: sub_df.hp.rank()
for (grp, sub_df) in X.itergroups()
})
def test_removes_infinite_values():
df = mtcars.copy()
df.loc[[0, 5], 'wt'] = [np.inf, -np.inf]
p = ggplot(df, aes(x='wt')) + geom_bar()
with pytest.warns(UserWarning) as record:
p._build()
def removed_2_row_with_infinites(record):
for item in record:
msg = str(item.message).lower()
if '2 rows' in msg and 'non-finite' in msg:
return True
return False
assert removed_2_row_with_infinites(record)
def test_removes_infinite_values():
df = mtcars.copy()
df.loc[[0, 5], 'wt'] = [np.inf, -np.inf]
p = ggplot(df, aes(x='wt')) + geom_bar()
with pytest.warns(UserWarning) as record:
p._build()
def removed_2_row_with_infinites(record):
for item in record:
msg = str(item.message).lower()
if '2 rows' in msg and 'non-finite' in msg:
return True
return False
assert removed_2_row_with_infinites(record)
(ggplot(mtcars, aes('wt', 'mpg', color='factor(gear)')) + geom_point() + stat_smooth(method='lm') + facet_wrap('~gear'))
from plotnine import *
(ggplot(mtcars, aes('factor(cyl)', fill='factor(am)')) + geom_bar( position='fill') )
(ggplot(mtcars, aes('factor(cyl)', fill='factor(am)')) + geom_bar(position='fill') + geom_text(aes(label='stat(count)'), stat='count', position='fill' ))
(ggplot(mpg)+ aes(x='manufacturer') + geom_bar(size=20) + coord_flip() + labs(y='Count', x='Manufacturer', title='Number of Cars by Make'))
#https://plotnine.readthedocs.io/en/stable/tutorials/miscellaneous-order-plot-series.html
from pydataset import data
data()
mtcars = data('mtcars')
data1 = mtcars.copy()
data1.head()
mpg = data('mpg')
data2 = mpg.copy()
data2.head()
#barplot
(mpg['manufacturer'].value_counts(sort=False).plot.barh().set_title('Number of Cars by Make'))
#histogram
(mpg['cty'].plot.hist(bins=12))
plt.hist('cty', bins=12, data=mpg)
ggplot(mpg) + aes(x='cty') + geom_histogram(binwidth=2) #plotnine