def calc_hist(srs: dd.Series, bins: int,
orig_df_len: int) -> Tuple[pd.DataFrame, float]:
"""
Calculate a histogram over a given series.
Parameters
----------
srs : dd.Series
one numerical column over which to compute the histogram
bins : int
number of bins to use in the histogram
orig_df_len : int
length of the original dataframe
Returns
-------
Tuple[pd.DataFrame, float]:
The histogram in a dataframe and the percent of missing values
"""
miss_pct = round(srs.isna().sum() / len(srs) * 100, 1)
data = srs.dropna().values
if len(data) == 0: # all values in column are missing
return pd.DataFrame({"left": [], "right": [], "freq": []}), miss_pct
minv, maxv = data.min(), data.max()
hist_arr, bins_arr = np.histogram(data, range=[minv, maxv], bins=bins)
intervals = _format_bin_intervals(bins_arr)
hist_df = pd.DataFrame({
"intervals": intervals,
"left": bins_arr[:-1],
"right": bins_arr[1:],
"freq": hist_arr,
"pct": hist_arr / orig_df_len * 100,
})
return hist_df, miss_pct
def calc_bar_pie(srs: dd.Series, ngroups: int,
largest: bool) -> Tuple[pd.DataFrame, int, float]:
"""
Calculates the group counts given a series.
Parameters
----------
srs
One categorical column
ngroups
Number of groups to return
largest
If true, show the groups with the largest count,
else show the groups with the smallest count
Returns
-------
Tuple[pd.DataFrame, float]
A dataframe of the group counts, the total count of groups,
and the percent of missing values
"""
miss_pct = round(srs.isna().sum() / len(srs) * 100, 1)
try:
grp_srs = srs.groupby(srs).size()
except TypeError:
srs = srs.astype(str)
grp_srs = srs.groupby(srs).size()
# select largest or smallest groups
smp_srs = grp_srs.nlargest(n=ngroups) if largest else grp_srs.nsmallest(
n=ngroups)
df = smp_srs.to_frame().rename(columns={srs.name: "cnt"}).reset_index()
# add a row containing the sum of the other groups
other_cnt = len(srs) - df["cnt"].sum()
df = df.append(pd.DataFrame({srs.name: ["Others"], "cnt": [other_cnt]}))
# add a column containing the percent of count in each group
df["pct"] = df["cnt"] / len(srs) * 100
df.columns = ["col", "cnt", "pct"]
df["col"] = df["col"].astype(
str) # needed when numeric is cast as categorical
return df, len(grp_srs), miss_pct