def surgery_usage_regression_df(surgery_df,
usage_df,
item_ids=[],
case_cart_df=None,
filters=[],
common_events=True):
surgery_df = Analytics.process_filters(surgery_df, filters)
surgery_df = surgery_df.drop_duplicates(subset=["event_id"])
usage_df = Analytics.process_filters(usage_df, filters)
if case_cart_df:
case_cart_df = Analytics.process_filters(case_cart_df, filters)
if common_events:
surgery_df = surgery_df[surgery_df["event_id"].isin(
set(usage_df["event_id"]))]
# usage_df = usage_df[usage_df["item_id"].isin(item_ids)]
# usage_df = usage_df.drop_duplicates(["event_id", "item_id"], keep="last")
# usage_df = usage_df.pivot(index="event_id", columns="item_id", values="used_qty") \
# .fillna(0) \
# .reset_index()
usage_df = usage_df.drop_duplicates(["event_id", "item_id"], keep="last")
usage_df = surgery_df[surgery_df["event_id"].isin(set(usage_df["event_id"]))] \
.join(usage_df[usage_df["item_id"].isin(item_ids)]
.pivot(index="event_id", columns="item_id", values="used_qty"),
on="event_id",
how="left",
rsuffix="item")\
.fillna(0)
procedure_df = pd.concat([
pd.Series(row['event_id'], row['procedures'])
for _, row in surgery_df.iterrows()
], ).reset_index().rename(columns={
"index": "procedure",
0: "event_id"
})
procedure_df["flag"] = 1
regression_df = procedure_df \
.pivot(index="event_id", columns="procedure", values="flag") \
.fillna(0) \
.reset_index() \
.join(usage_df.set_index("event_id"),
on="event_id",
how="left",
rsuffix="usage")
if common_events:
regression_df[item_ids] = regression_df[item_ids].fillna(0)
return regression_df
def dist(g_df):
print(0)
print(g_df.iloc[0])
g_df = g_df.groupby("start_date").agg({"event_id": "nunique"})
print(1)
data_df = pd.DataFrame()
data_df["dt"] = pd.date_range(start=start, end=end, freq='D')
data_df["date"] = data_df["dt"].apply(lambda x: x.date())
data_df = Analytics.process_day_df_columns(data_df)
data_df = data_df.join(g_df, on="date", how="left").fillna(0)
if day_filters:
print(2)
data_df = Analytics.process_filters(data_df, filters)
if day_group_by:
print(3)
data_df.groupby("day_groupby")
return data_df["event_id"].to_list()
def surgeries_per_day_distribution(df,
group_by=None,
filters=[],
day_group_by=None,
day_filters=[]):
df = Analytics.process_filters(df, filters)
start, end = min(df["start_date"]), max(df["start_date"])
if group_by:
def dist(g_df):
print(0)
print(g_df.iloc[0])
g_df = g_df.groupby("start_date").agg({"event_id": "nunique"})
print(1)
data_df = pd.DataFrame()
data_df["dt"] = pd.date_range(start=start, end=end, freq='D')
data_df["date"] = data_df["dt"].apply(lambda x: x.date())
data_df = Analytics.process_day_df_columns(data_df)
data_df = data_df.join(g_df, on="date", how="left").fillna(0)
if day_filters:
print(2)
data_df = Analytics.process_filters(data_df, filters)
if day_group_by:
print(3)
data_df.groupby("day_groupby")
return data_df["event_id"].to_list()
df = df.groupby(group_by)
return df.apply(lambda f: dist(f))
else:
g_df = df.groupby("start_date").agg({"event_id": "nunique"})
data_df = pd.DataFrame()
data_df["dt"] = pd.date_range(start=start, end=end, freq='D')
data_df["date"] = data_df["dt"].apply(lambda x: x.date())
data_df = Analytics.process_day_df_columns(data_df)
data_df = data_df.join(g_df, on="date", how="left").fillna(0)
if day_group_by:
return data_df.groupby(day_group_by).agg({"event_id": lambda x: list(x)})\
.reset_index()\
.rename(columns={"event_id": "data"})
else:
return data_df["event_id"].to_list()
return
def surgery_count_metric(df, group_by=None, filters=[]):
"""
returns a df with count of number of surgeries for each group of the group by dimension.
i.e. if group by case service, cardiac 5 meaning 5 surgeries total from cardiac department.
"""
df = Analytics.process_filters(df, filters)
return df[[group_by, "event_id"]] \
.groupby([group_by]) \
.agg({'event_id': 'nunique'}) \
.reset_index() \
.rename(columns={'event_id': 'metrix', group_by: 'dimension'})
def procedure_count_distribution(df, group_by=None, filters=[]):
df = Analytics.process_filters(df, filters)
df["procedure_count"] = df["procedures"].apply(lambda x: len(x))
if group_by:
return df.groupby(group_by)\
.agg({"procedure_count": lambda x: list(x)})\
.reset_index()\
.rename(columns={"procedure_count": "data"})
return df["procedure_count"].to_list()
def item_usage_per_day_distribution(df, group_by=None, filters=[]):
df = Analytics.process_filters(df, filters)
df["start_date"] = df["start_dt"].apply(lambda x: x.date())
start, end = min(df["start_date"]), max(df["start_date"])
if group_by:
df = df.groupby(group_by)
date_df = pd.DataFrame()
date_df["start_date"] = pd.date_range(start=start, end=end, freq='D')
date_df["start_date"] = date_df["start_date"].apply(lambda x: x.date())
def dist(g_df):
g_df = g_df.groupby("start_date").agg({"used_qty": "sum"})
data_df = date_df.join(g_df, on="start_date", how="left").fillna(0)
return data_df["used_qty"].to_list()
return df.apply(lambda f: dist(f))
def surgery_hours_metric(df, group_by=None, filters=[]):
"""
df should be surgery_df
returns df with total hours of surgeries in each group of the group by dimension.
i.e. cardiac 10hours
"""
df = Analytics.process_filters(df, filters)
df = df[df["surgery_duration"].notna()]
df = df[[group_by, "surgery_duration"]] \
.groupby([group_by]) \
.agg({'surgery_duration': 'sum'}) \
.reset_index() \
.rename(columns={'surgery_duration': 'metric', group_by: 'dimension'})
# to convert from seconds to hours
df["metric"] = df["metric"].apply(lambda x: x.days * 24 + x.seconds / 60)
return df
def item_usage_per_week_distribution(usage_df, group_by=None, filters=[]):
usage_df = Analytics.process_filters(usage_df, filters)
usage_df["week"] = usage_df["start_dt"].apply(lambda x: "{0}-{1}".format(
str(x.year - 1
if (x.month == 1 and x.week == 52) else x.year), str(x.week)))
start, end = min(usage_df["start_dt"]), max(usage_df["start_dt"])
if group_by:
usage_df = usage_df.groupby(group_by)
date_df = pd.DataFrame()
date_df["start_date"] = pd.date_range(start=start, end=end, freq='W')
date_df["week"] = date_df["start_date"].apply(lambda x: "{0}-{1}".format(
str(x.year - 1
if (x.month == 1 and x.week == 52) else x.year), str(x.week)))
date_df = date_df[["week"]]
def dist(g_df):
g_df = g_df.groupby("week").agg({"used_qty": "sum"})
data_df = date_df.join(g_df, on="week", how="left").fillna(0)
return data_df["used_qty"].to_list()
return usage_df.apply(lambda f: dist(f))
def run(case_service="Cardiac Surgery", item_id="1686"):
analytics = ScmAnalytics.ScmAnalytics(lhs_config)
case_service_filter = [{
"dim": "case_service",
"op": "eq",
"val": case_service
}]
usage_df = analytics.usage_df
usage_df = usage_df[usage_df["start_date"].notna()]
usage_df = Analytics.process_filters(usage_df, filters=case_service_filter)
usage_events = set(usage_df["event_id"])
item_usage_df = usage_df[usage_df["item_id"] == item_id]
surgery_df = pre_process_columns(analytics.surgery_df)
surgery_df = surgery_df[surgery_df["start_date"].notna()]
surgery_df = surgery_df[
surgery_df["start_date"] > datetime.date(2016, 1, 1)]
surgery_df = Analytics.process_filters(surgery_df,
filters=case_service_filter)
surgery_df = surgery_df[surgery_df["event_id"].isin(usage_events)]
surgery_df = surgery_df.join(
item_usage_df.set_index("event_id")[["used_qty"]],
on="event_id",
how="left").fillna(0)
surgery_df["procedures"] = surgery_df["procedures"].apply(
lambda x: frozenset(x))
usage_dist = surgery_df.groupby(["procedures"]).agg({
"used_qty":
lambda x: list(x)
}).reset_index()
usage_dist["occurrences"] = usage_dist["used_qty"].apply(lambda x: len(x))
usage_dist = usage_dist[usage_dist["occurrences"] > 25]
usage_dist["mean"] = usage_dist["used_qty"].apply(lambda x: np.mean(x))
usage_dist["variance"] = usage_dist["used_qty"].apply(
lambda x: np.var(x, ddof=1))
usage_dist["var/mean"] = usage_dist["variance"] / usage_dist["mean"]
df = surgery_df[surgery_df["procedures"].isin(
usage_dist["procedures"])][["start_date", "used_qty"]]
rolling_df = df[["used_qty"]].rolling(100).mean()
plt.plot(list(rolling_df["used_qty"]))
rolling_df = df[["used_qty"]].rolling(50).mean()
plt.plot(list(rolling_df["used_qty"]))
plt.savefig("{}_rolling_usage.png".format(item_id), format="png")
traces = []
x_max = 0
for i in range(len(usage_dist)):
case = usage_dist.iloc[i]["procedures"]
data = usage_dist.iloc[i]["used_qty"]
label = ", ".join(case)
end = max(usage_dist.iloc[i]["used_qty"]) + 1
traces.append(
go.Histogram(x=data,
name=label,
xbins=dict(start=0, end=end, size=1),
histnorm='probability',
opacity=0.75))
x_max = int(end) if end > x_max else x_max
def boostrap_info_process(item_id="38242"):
case_service = "Cardiac Surgery"
#item_id = "3824ns_info_state_rvs2"
info_granularity = 1
eps_trunk = 1e-3
elective_outdir = "scm_implementation/ns_info_state_rvs/elective"
emergency_outdir = "scm_implementation/ns_info_state_rvs/emergency"
analytics = ScmAnalytics.ScmAnalytics(lhs_config)
filters = [{
"dim": "case_service",
"op": "eq",
"val": case_service
}, {
"dim": "urgent_elective",
"op": "eq",
"val": "Elective"
}]
elective_filter = [{
"dim": "urgent_elective",
"op": "eq",
"val": "Elective"
}]
emergency_filter = [{
"dim": "urgent_elective",
"op": "eq",
"val": "Urgent"
}]
case_service_filter = [{
"dim": "case_service",
"op": "eq",
"val": case_service
}]
surgery_df = pre_process_columns(analytics.surgery_df)
surgery_df = surgery_df[surgery_df["start_date"].notna()]
surgery_df = surgery_df[
surgery_df["start_date"] > datetime.date(2016, 1, 1)]
surgery_df = Analytics.process_filters(surgery_df,
filters=elective_filter +
case_service_filter)
dist_df = surgeries_per_day_distribution(surgery_df,
day_group_by="is_weekday",
filters=[])
data = dist_df.set_index("is_weekday").loc[True]["data"]
bins = range(1 + int(max(data)))
binom_x = [x + 0.5 for x in bins]
n = int(max(data))
p = np.mean(data) / n
surgery_df = pre_process_columns(analytics.surgery_df)
surgery_df = surgery_df[surgery_df["start_date"].notna()]
surgery_df = surgery_df[
surgery_df["start_date"] > datetime.date(2016, 1, 1)]
surgery_df = Analytics.process_filters(surgery_df,
filters=emergency_filter +
case_service_filter)
dist_df = surgeries_per_day_distribution(surgery_df, filters=[])
emergency_surgeries_mean = np.mean(dist_df)
surgery_df = Analytics.process_filters(analytics.surgery_df,
filters=case_service_filter)
surgery_df["procedure_count"] = surgery_df["procedures"].apply(
lambda x: len(x))
procedure_count_df = surgery_df.groupby("procedure_count").agg({
"event_id":
"count"
}).reset_index()
procedure_count_df = procedure_count_df[
procedure_count_df["procedure_count"] != 6]
procedure_count_df["p"] = procedure_count_df["procedure_count"] / sum(
procedure_count_df["procedure_count"])
procedure_count_rv = pacal.DiscreteDistr(
procedure_count_df["procedure_count"], procedure_count_df["p"])
"""
Procedure weights
"""
usage_events = set(analytics.usage_df["event_id"])
surgery_df = analytics.surgery_df[analytics.surgery_df["event_id"].isin(
usage_events)]
surgery_df = Analytics.process_filters(surgery_df,
filters=case_service_filter)
surgery_df["procedures"] = surgery_df["procedures"].apply(
lambda x: set(e.replace(" ", "_") for e in x))
procedures = surgery_df["procedures"].apply(lambda x: list(x)).to_list()
procedures = pd \
.DataFrame({"procedure": [val for sublist in procedures for val in sublist],
"count": [1 for sublist in procedures for val in sublist]}) \
.groupby("procedure") \
.agg({"count": "count"}) \
.reset_index()
procedures["p"] = procedures["count"] / sum(procedures["count"])
def procedure_pick_rv(size):
return np.random.choice(procedures["procedure"],
p=procedures["p"],
replace=False,
size=size)
synthetic_surgeries = pd.DataFrame({"event_id": list(range(1000))})
synthetic_surgeries["procedure_count"] = procedure_count_rv.rand(1000)
synthetic_surgeries["procedures"] = synthetic_surgeries[
"procedure_count"].apply(lambda x: procedure_pick_rv(x))
synthetic_procedure_df = pd.concat(
[pd.Series(row['event_id'], row['procedures']) for _, row in synthetic_surgeries.iterrows()]) \
.reset_index() \
.rename(columns={"index": "procedure",
0: "event_id"}
)
synthetic_procedure_df["flag"] = 1
synthetic_surgeries_df = synthetic_procedure_df \
.pivot(index="event_id", columns="procedure", values="flag") \
.fillna(0) \
.reset_index()
feature_df = pd.read_csv(os.path.join("regression_results", item_id))
features = feature_df["feature"]
featured_procedures = list(
filter(lambda x: "." not in x, feature_df["feature"]))
if "other" in featured_procedures:
featured_procedures.remove("other")
for fp in featured_procedures:
if fp not in synthetic_surgeries_df:
print(procedures.set_index("procedure").loc[fp])
synthetic_surgeries_df[fp] = 0
all_procedures = set.union(*surgery_df["procedures"])
interactions = list(filter(lambda x: "." in x, feature_df["feature"]))
interactions = list(Interaction(i.split(".")) for i in interactions)
data, _ = SURegressionModel.extract_features_data(synthetic_surgeries_df,
featured_procedures, [],
interactions,
other=True)
for f in feature_df["feature"]:
if f not in data:
print(f)
data[f] = 0
synthetic_surgeries_df["feature_vector"] = data[features].values.tolist()
coeff = np.array(feature_df["estimate"])
synthetic_surgeries_df["expected_usage"] = synthetic_surgeries_df["feature_vector"] \
.apply(lambda x: np.exp(np.dot(x, coeff)))
"""
Information rv for empirical surgeries
"""
surgery_df = surgery_df.drop_duplicates("event_id", keep="last")
empirical_procedure_df = pd.concat(
[pd.Series(row['event_id'], row['procedures']) for _, row in surgery_df.iterrows()]) \
.reset_index() \
.rename(columns={"index": "procedure",
0: "event_id"}
)
empirical_procedure_df["flag"] = 1
empirical_surgeries_df = empirical_procedure_df \
.pivot(index="event_id", columns="procedure", values="flag") \
.fillna(0) \
.reset_index()
data, _ = SURegressionModel.extract_features_data(empirical_surgeries_df,
featured_procedures, [],
interactions,
other=True)
empirical_surgeries_df["feature_vector"] = data[features].values.tolist()
empirical_surgeries_df["expected_usage"] = empirical_surgeries_df["feature_vector"] \
.apply(lambda x: np.exp(np.dot(x, coeff)))
"""
Plotly histogram for per surgery info rv, empirical surgeries and synthetic using regression results
"""
s = 0
e = int(
max(max(empirical_surgeries_df["expected_usage"]),
max(synthetic_surgeries_df["expected_usage"])) + 1)
empirical_trace = go.Histogram(
x=empirical_surgeries_df["expected_usage"],
name='Empirical Surgery Info RV (mean={:0.2f})'.format(
np.mean(empirical_surgeries_df["expected_usage"])),
xbins=dict(start=s, end=e, size=info_granularity),
histnorm='probability density',
opacity=0.75)
synthetic_trace = go.Histogram(
x=synthetic_surgeries_df["expected_usage"],
name='Synthetic Surgery Info RV (mean={:0.2f})'.format(
np.mean(synthetic_surgeries_df["expected_usage"])),
xbins=dict(start=s, end=e, size=info_granularity),
histnorm='probability density',
opacity=0.75)
layout = go.Layout(title="Per Surgery Info R.V Item: {0}".format(item_id),
xaxis={'title': 'Info [Expected Usage]'},
yaxis={'title': 'Probability Density'})
figure = go.Figure(data=[empirical_trace, synthetic_trace], layout=layout)
plot(figure, filename="{0}_Per_Surgery_Info_Rv.html".format(item_id))
"""
Plotly histogram for per weekday elective surgery RV
"""
empirical_rv_df = empirical_surgeries_df.groupby(["expected_usage"]) \
.agg({"event_id": "count"}) \
.rename(columns={"event_id": "count"}) \
.reset_index()
empirical_rv_df["p"] = empirical_rv_df["count"] / sum(
empirical_rv_df["count"])
emp_surgery_rv = pacal.DiscreteDistr(empirical_rv_df["expected_usage"],
empirical_rv_df["p"])
surgery_demand_rv = pacal.BinomialDistr(n, p)
days = 100000
elective_samples = [
sum(emp_surgery_rv.rand(x)) for x in np.random.binomial(n, p, days)
]
elective_samples = [
round(sample / info_granularity) * info_granularity
for sample in elective_samples
]
weekday_elective_trace = go.Histogram(
x=elective_samples,
name='{} Elective Info RV (mean={:0.2f})'.format(
item_id, np.mean(elective_samples)),
xbins=dict(start=0, end=max(elective_samples), size=info_granularity),
histnorm='probability',
opacity=0.75)
"""
Plotly histogram for per day emergency surgery RV
"""
emergency_samples = [
sum(emp_surgery_rv.rand(x))
for x in np.random.poisson(emergency_surgeries_mean, days)
]
emergency_samples = [
round(sample / info_granularity) * info_granularity
for sample in emergency_samples
]
emergency_trace = go.Histogram(
x=emergency_samples,
name='{} Emergency Info RV (mean={:0.2f})'.format(
item_id, np.mean(emergency_samples)),
xbins=dict(start=0, end=max(emergency_samples), size=info_granularity),
histnorm='probability',
opacity=0.75)
layout = go.Layout(
title="Weekday Elective Info R.V Item: {0}".format(item_id),
xaxis={'title': 'Info State (Poisson Usage)]'},
yaxis={'title': 'Probability'})
figure = go.Figure(data=[weekday_elective_trace, emergency_trace],
layout=layout)
plot(figure, filename="{0}_Weekday_Elective_Info_Rv.html".format(item_id))
elective_info_df = pd.DataFrame({"info": elective_samples, "count": [1] * len(elective_samples)}) \
.groupby(["info"]) \
.agg({"count": "count"}) \
.reset_index()
elective_info_df["p"] = elective_info_df["count"] / sum(
elective_info_df["count"])
elective_info_rv = pacal.DiscreteDistr(elective_info_df["info"],
elective_info_df["p"])
emergency_info_df = pd.DataFrame({"info": emergency_samples, "count": [1] * len(emergency_samples)}) \
.groupby(["info"]) \
.agg({"count": "count"}) \
.reset_index()
emergency_info_df["p"] = emergency_info_df["count"] / sum(
emergency_info_df["count"])
emergency_info_rv = pacal.DiscreteDistr(emergency_info_df["info"],
emergency_info_df["p"])
max_v = 999
for d in elective_info_rv.get_piecewise_pdf().getDiracs():
if 1 - elective_info_rv.cdf(d.a) < eps_trunk:
max_v = d.a
break
diracs = (pacal.CondLtDistr(elective_info_rv, max_v)) \
.get_piecewise_pdf().getDiracs()
diracs = list(filter(lambda d: d.f > 0, diracs))
elective_info_rv = pacal.DiscreteDistr([d.a for d in diracs],
[d.f for d in diracs])
max_v = 999
for d in emergency_info_rv.get_piecewise_pdf().getDiracs():
if 1 - emergency_info_rv.cdf(d.a) < eps_trunk:
max_v = d.a
break
diracs = (pacal.CondLtDistr(emergency_info_rv, max_v)) \
.get_piecewise_pdf().getDiracs()
diracs = list(filter(lambda d: d.f > 0, diracs))
emergency_info_rv = pacal.DiscreteDistr([d.a for d in diracs],
[d.f for d in diracs])
with open(os.path.join(elective_outdir, "{0}.pickle".format(item_id)),
"wb") as f:
pickle.dump(elective_info_rv, f)
with open(os.path.join(emergency_outdir, "{0}.pickle".format(item_id)),
"wb") as f:
pickle.dump(emergency_info_rv, f)
return emergency_trace, weekday_elective_trace
from os import path
import plotly.plotly as py
import plotly.graph_objs as go
import numpy as np
import datetime
case_service = "All"
analytics = ScmAnalytics.ScmAnalytics(lhs_config)
for case_service in set(analytics.surgery_df["case_service"]):
case = {"dim": "case_service", "op": "==", "val": case_service}
elec = {"dim": "urgent_elective", "op": "==", "val": "Elective"}
surgery_df = Analytics.process_filters(analytics.surgery_df,
filters=[case, elec])
if len(surgery_df) < 1:
continue
# surgery_df = Analytics.process_filters(analytics.surgery_df, filters=[elec])
surgery_df["is_weekday"] = surgery_df["start_date"].apply(
lambda x: True if x.weekday() < 5 else False)
surgery_df = surgery_df[surgery_df["is_weekday"]]
surgery_df = surgery_df.drop_duplicates("event_id", keep="last")
surgery_df = surgery_df[
surgery_df["start_date"] > datetime.date(2016, 1, 1)]
surgeries_per_day = surgery_df.groupby("start_date") \
.agg({"event_id": "nunique"}) \
.rename(columns={"event_id": "n_surgery_day"})
"21920", "38197", "82099"
]
case_service = "Cardiac Surgery"
#item_id = "47320"
analytics = ScmAnalytics.ScmAnalytics(lhs_config)
case_service_filter = [{
"dim": "case_service",
"op": "eq",
"val": case_service
}]
usage_events = set(analytics.usage_df["event_id"])
surgery_df = analytics.surgery_df[analytics.surgery_df["event_id"].isin(
usage_events)]
surgery_df = Analytics.process_filters(surgery_df, filters=case_service_filter)
surgery_df["procedures"] = surgery_df["procedures"].apply(
lambda x: set(e.replace(" ", "_") for e in x))
surgery_df = surgery_df.drop_duplicates("event_id", keep="last")
extracted_surgery_df = surgery_df[["event_id"]]
empirical_procedure_df = pd.concat(
[pd.Series(row['event_id'], row['procedures']) for _, row in surgery_df.iterrows()]) \
.reset_index() \
.rename(columns={"index": "procedure",
0: "event_id"}
)
empirical_procedure_df["flag"] = 1
empirical_surgeries_df = empirical_procedure_df \
.pivot(index="event_id", columns="procedure", values="flag") \
.fillna(0) \
def lead_time_distribution(df, groupby=None, filters=[]):
df = Analytics.process_filters(df, filters)
return df["order_leadtime"].dt.days
def run(case_service="Cardiac Surgery", item_id="1686", procedure_set=None):
analytics = ScmAnalytics.ScmAnalytics(lhs_config)
case_service_filter = [{
"dim": "case_service",
"op": "eq",
"val": case_service
}]
usage_df = analytics.usage_df
usage_df = usage_df[usage_df["start_date"].notna()]
usage_df = Analytics.process_filters(usage_df, filters=case_service_filter)
usage_events = set(usage_df["event_id"])
item_usage_df = usage_df[usage_df["item_id"] == item_id]
surgery_df = pre_process_columns(analytics.surgery_df)
surgery_df = surgery_df[surgery_df["start_date"].notna()]
surgery_df = surgery_df[
surgery_df["start_date"] > datetime.date(2016, 1, 1)]
surgery_df = Analytics.process_filters(surgery_df,
filters=case_service_filter)
surgery_df = surgery_df[surgery_df["event_id"].isin(usage_events)]
surgery_df = surgery_df.join(
item_usage_df.set_index("event_id")[["used_qty"]],
on="event_id",
how="left").fillna(0)
surgery_df["procedures"] = surgery_df["procedures"].apply(
lambda x: frozenset(x))
surgery_df = surgery_df[surgery_df["procedures"] == procedure_set]
traces = []
x_max = int(max(surgery_df["used_qty"])) + 1
data = surgery_df["used_qty"]
label = ", ".join(procedure_set)
fn = "__".join(procedure_set)
fn = "Usage_Dist_item_" + item_id + "_" + fn.replace(" ", "_")
#
# traces.append(go.Histogram(
# x=data,
# name=label,
# xbins=dict(
# start=0,
# end=x_max,
# size=1
# ),
# histnorm='probability',
# opacity=1,
#
# ))
#
# tickvals = list(x + 0.5 for x in range(x_max))
# ticktext = list(str(x) for x in range(x_max))
# layout = go.Layout( # title="Item: {} Empirical Usage Distribution for common cases".format(item_id),
# xaxis={'title': 'Used Qty',
# 'tickvals': tickvals,
# 'ticktext': ticktext},
# yaxis={'title': 'Probability'},
# font={"size": 16},
# plot_bgcolor="white",
# bargap=0.2)
# figure = go.Figure(
# data=traces,
# layout=layout,
# )
# # figure.update_xaxes(showgrid=True, gridwidth=1, gridcolor='lightgrey')
# figure.update_yaxes(showgrid=True, gridwidth=1, gridcolor='lightgrey')
# # plot(figure, filename="{}_empircal_usage_distribution.html".format(item_id))
# figure.write_image(fn, width=900, height=600)
import matplotlib
import matplotlib.ticker as plticker
matplotlib.rcParams.update({'font.size': 12})
plt.figure(figsize=(4, 3.5))
plt.tight_layout()
plt.gcf().subplots_adjust(bottom=0.15, left=0.15)
n, bins, patches = plt.hist(data,
range(x_max + 1),
density=True,
facecolor='#08306b',
rwidth=0.95)
spacing = np.round((max(n) + 0.1) / 4, decimals=1)
plt.yticks(np.arange(0, max(n) + 0.1, spacing))
#matplotlib.pyplot.grid(b=True, which='major', axis='y')
plt.ylabel("Probability")
plt.xlabel("Used Quantity")
plt.xticks(range(x_max + 1))
plt.savefig(fn + ".svg", format='svg')
plt.savefig(fn + ".eps", format='eps')