day zero of graph is now the user inputted date_first_hospitalized

Author: quinn-dougherty

src/penn_chime/charts.py

@@ -26,7 +26,7 @@ def new_admissions_chart(
 
     tooltip_dict = {False: "day", True: "date:T"}
     if as_date:
-        projection_admits = add_date_column(projection_admits)
+        projection_admits = add_date_column(projection_admits, parameters.date_first_hospitalized)
         x_kwargs = {"shorthand": "date:T", "title": "Date", "axis": alt.Axis(format=(DATE_FORMAT))}
     else:
         x_kwargs = {"shorthand": "day", "title": "Days from today"}
@@ -66,7 +66,7 @@ def admitted_patients_chart(
     max_y_axis = parameters.max_y_axis
     as_date = parameters.as_date
     if as_date:
-        census = add_date_column(census)
+        census = add_date_column(census, parameters.date_first_hospitalized)
         x_kwargs = {"shorthand": "date:T", "title": "Date", "axis": alt.Axis(format=(DATE_FORMAT))}
         idx = "date:T"
     else:
@@ -113,7 +113,7 @@ def additional_projections_chart(
     max_y_axis = parameters.max_y_axis
 
     if as_date:
-        dat = add_date_column(dat)
+        dat = add_date_column(dat, parameters.date_first_hospitalized)
         x_kwargs = {"shorthand": "date:T", "title": "Date", "axis": alt.Axis(format=(DATE_FORMAT))}
     else:
         x_kwargs = {"shorthand": "day", "title": "Days from today"}

src/penn_chime/models.py

@@ -78,8 +78,8 @@ def __init__(self, p: Parameters):
             p.n_days,
         )
         dispositions_df = build_dispositions_df(raw_df, rates, p.market_share)
-        admits_df = build_admits_df(dispositions_df)
-        census_df = build_census_df(admits_df, lengths_of_stay)
+        admits_df = build_admits_df(dispositions_df, p.n_days_since_first_hospitalized)
+        census_df = build_census_df(admits_df, lengths_of_stay, p.n_days_since_first_hospitalized)
 
         self.susceptible = susceptible
         self.infected = infected
@@ -112,8 +112,8 @@ def __init__(self, p: Parameters):
                     argmin_dt = dt
             self.census_df = censes[dt]
             p.doubling_time = argmin_dt
-            #
-            # update all state dependent on doubling time.
+
+            # update all state that is dependent on doubling time.
             intrinsic_growth_rate = self._intrinsic_growth_rate(p.doubling_time)
             gamma = 1 / recovery_days
             beta = self._beta(intrinsic_growth_rate, gamma, susceptible, p.relative_contact_rate)
@@ -129,8 +129,8 @@ def __init__(self, p: Parameters):
                 p.n_days
             )
             dispositions_df = build_dispositions_df(raw_df, rates, p.market_share)
-            admits_df = build_admits_df(dispositions_df)
-            census_df = build_census_df(admits_df, lengths_of_stay)
+            admits_df = build_admits_df(dispositions_df, p.n_days_since_first_hospitalized)
+            census_df = build_census_df(admits_df, lengths_of_stay, p.n_days_since_first_hospitalized)
 
             self.intrinsic_growth_rate = intrinsic_growth_rate
             self.gamma = gamma
@@ -167,9 +167,21 @@ def run_projection(self, p: Parameters, doubling_time: float) -> pd.DataFrame:
 
         raw_df = sim_sir_df(S,I,R,beta,gamma,n_days)
 
-        dispositions_df = build_dispositions_df(raw_df, self._rates, p.market_share)
-        admits_df = build_admits_df(dispositions_df)
-        census_df = build_census_df(admits_df, self._lengths_of_stay)
+        # dispositions_df = build_dispositions_df(raw_df, self._rates, p.market_share)
+
+        i_dict_v = get_dispositions(raw_df.infected, self._rates, market_share)
+        r_dict_v = get_dispositions(raw_df.recovered, self._rates, market_share)
+
+        dispositions = {
+            key: value + r_dict_v[key]
+            for key, value in i_dict_v.items()
+        }
+
+        dispositions_df = pd.DataFrame(dispositions)
+        dispositions_df = dispositions_df.assign(day=dispositions_df.index)
+
+        admits_df = build_admits_df(dispositions_df, p.n_days_since_first_hospitalized)
+        census_df = build_census_df(admits_df, self._lengths_of_stay, p.n_days_since_first_hospitalized)
         return census_df
 
     def loss_dt(self, p: Parameters) -> float:
@@ -245,6 +257,19 @@ def sim_sir_df(
         columns=("day", "susceptible", "infected", "recovered"),
     )
 
+
+def get_dispositions(
+    patients: np.ndarray,
+    rates: Dict[str, float],
+    market_share: float,
+) -> Dict[str, np.ndarray]:
+    """Get dispositions of patients adjusted by rate and market_share."""
+    return {
+        key: patients * rate * market_share
+        for key, rate in rates.items()
+    }
+
+
 def build_dispositions_df(
     sim_sir_df: pd.DataFrame,
     rates: Dict[str, float],
@@ -261,16 +286,20 @@ def build_dispositions_df(
     })
 
 
-def build_admits_df(dispositions_df: pd.DataFrame) -> pd.DataFrame:
+def build_admits_df(dispositions_df: pd.DataFrame, n_days_since_first_hospitalized: int) -> pd.DataFrame:
     """Build admits dataframe from dispositions."""
     admits_df = dispositions_df.iloc[:-1, :] - dispositions_df.shift(1)
-    admits_df.day = dispositions_df.day
+    if n_days_since_first_hospitalized is not None:
+        admits_df.day = dispositions_df.day - n_days_since_first_hospitalized
+    else:
+        admits_df.day = dispositions_df.day
     return admits_df
 
 
 def build_census_df(
     admits_df: pd.DataFrame,
     lengths_of_stay: Dict[str, int],
+    n_days_since_first_hospitalized: int
 ) -> pd.DataFrame:
     """Average Length of Stay for each disposition of COVID-19 case (total guesses)"""
     return pd.DataFrame({
@@ -285,30 +314,6 @@ def build_census_df(
     })
 
 
-############################
-##  ARGMIN DOUBLING_TIME  ##
-############################
-
-
-def observed_predicted_loss(self, doubling_time: float, p: Parameters) -> float:
-    """Squared error between predicted value and actual value
-
-    Won't be run if n_days_since_first_hospitalized is None
-    """
-    census_df = self.run_projection(p, dt=doubling_time)
-    ## get the predicted number hospitalized today
-    pred_current_hospitalized = self.census_df['hospitalized'].loc[p.n_days_since_first_hospitalized]
-
-    ## compare against the actual (user inputed) number
-    ## squared difference is the loss to be optimized
-    return (p.current_hospitalized - pred_current_hospitalized)**2
-
-def argmin_dt(self, doubling_times: np.ndarray, p: Parameters) -> float:
-    """Argmin of the loss function with respect to doubling time."""
-    loss = np.array([self.observed_predicted_loss(dt, p) for dt in doubling_times])
-    fitted_doubling_time = doubling_times[loss.argmin()]
-    return fitted_doubling_time
-
 
 #############
 ##  UTILS  ##

src/penn_chime/parameters.py

@@ -49,8 +49,10 @@ def __init__(
         self.n_days = n_days
         self.recovery_days = recovery_days
         if date_first_hospitalized:
+            self.date_first_hospitalized = date_first_hospitalized # needed for utils.add_date_column
             self.n_days_since_first_hospitalized = (date.today() - date_first_hospitalized).days
         else:
+            self.date_first_hospitalized = None # needed for utils.add_date_column
             self.n_days_since_first_hospitalized = None
 
         self.labels = {

src/penn_chime/presentation.py

@@ -464,7 +464,12 @@ def show_additional_projections(
 
 
 def draw_projected_admissions_table(
-    st, projection_admits: pd.DataFrame, labels, day_range, as_date: bool = False
+        st,
+        projection_admits: pd.DataFrame,
+        labels,
+        day_range,
+        date_first_hospitalized: Optional[date] = None,
+        as_date: bool = False
 ):
     admits_table = projection_admits[np.mod(projection_admits.index, day_range) == 0].copy()
     admits_table["day"] = admits_table.index
@@ -473,7 +478,7 @@ def draw_projected_admissions_table(
 
     if as_date:
         admits_table = add_date_column(
-            admits_table, drop_day_column=True, date_format=DATE_FORMAT
+            admits_table, date_first_hospitalized, drop_day_column=True, date_format=DATE_FORMAT
         )
     admits_table.rename(labels)
     st.table(admits_table)

src/penn_chime/utils.py

@@ -1,7 +1,7 @@
 """Utils."""
 
 from collections import namedtuple
-from datetime import datetime, timedelta
+from datetime import datetime, timedelta, date
 from typing import Optional
 from base64 import b64encode
 
@@ -36,7 +36,7 @@
 
 
 def add_date_column(
-    df: pd.DataFrame, drop_day_column: bool = False, date_format: Optional[str] = None,
+    df: pd.DataFrame, date_first_hospitalized: Optional[date], drop_day_column: bool = False, date_format: Optional[str] = None,
 ) -> pd.DataFrame:
     """Copies input data frame and converts "day" column to "date" column
 
@@ -65,7 +65,13 @@ def add_date_column(
 
     # Allocate (day) continous range for dates
     n_days = int(df.day.max())
-    start = datetime.now()
+
+    today = date.today()
+    if date_first_hospitalized:
+        delta = today - date_first_hospitalized
+        start = today - delta
+    else:
+        start = today
     end = start + timedelta(days=n_days + 1)
     # And pick dates present in frame
     dates = pd.date_range(start=start, end=end, freq="D")[df.day.tolist()]