Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

✨ flu: use only positive and negative tests in denominator #3271

Draft
wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

✨ flu: use only positive and negative tests in denominator #3271

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cb6ce20
using only pos+neg tests in denominator
spoonerf Sep 11, 2024
dbe25d0
fix
spoonerf Sep 11, 2024
ebc117d
updating explorer too
spoonerf Sep 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 16 additions & 16 deletions etl/steps/data/garden/who/2024-09-09/flu_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,28 +194,28 @@ def calculate_percent_positive(tb: Table, surveillance_cols: list[str]) -> Table
"inf_negative" + col,
] = np.nan
# Calculating the denominator separately
tb["denom_1" + col] = tb["inf_all" + col] + tb["inf_negative" + col]
tb["denom_2" + col] = tb["spec_processed_nb" + col]
tb["denom_3" + col] = tb["spec_received_nb" + col]
tb["denom" + col] = tb["inf_all" + col] + tb["inf_negative" + col]
# tb["denom_2" + col] = tb["spec_processed_nb" + col]
# tb["denom_3" + col] = tb["spec_received_nb" + col]

tb["pcnt_pos_1" + col] = (tb["inf_all" + col] / (tb["denom_1" + col])) * 100
tb["pcnt_pos_2" + col] = (tb["inf_all" + col] / (tb["denom_2" + col])) * 100
tb["pcnt_pos_3" + col] = (tb["inf_all" + col] / (tb["denom_3" + col])) * 100
tb["pcnt_pos" + col] = (tb["inf_all" + col] / (tb["denom" + col])) * 100
# tb["pcnt_pos_2" + col] = (tb["inf_all" + col] / (tb["denom_2" + col])) * 100
# tb["pcnt_pos_3" + col] = (tb["inf_all" + col] / (tb["denom_3" + col])) * 100

# hierachically fill the 'pcnt_pos' column with values from the columns described above in order of preference: 1->2->3
tb["pcnt_pos" + col] = tb["pcnt_pos_1" + col]
tb["denom" + col] = tb["denom_1" + col]
tb["pcnt_pos" + col] = tb["pcnt_pos" + col]
tb["denom" + col] = tb["denom" + col]

idx_2 = tb["pcnt_pos" + col].isna()
tb.loc[idx_2, "pcnt_pos" + col] = tb["pcnt_pos_2" + col]
tb.loc[idx_2, "denom" + col] = tb["denom_2" + col]
# idx_2 = tb["pcnt_pos" + col].isna()
# tb.loc[idx_2, "pcnt_pos" + col] = tb["pcnt_pos_2" + col]
# tb.loc[idx_2, "denom" + col] = tb["denom_2" + col]

idx_3 = tb["pcnt_pos" + col].isna()
tb.loc[idx_3, "pcnt_pos" + col] = tb["pcnt_pos_2" + col]
tb.loc[idx_3, "denom" + col] = tb["denom_2" + col]
# idx_3 = tb["pcnt_pos" + col].isna()
# tb.loc[idx_3, "pcnt_pos" + col] = tb["pcnt_pos_2" + col]
# tb.loc[idx_3, "denom" + col] = tb["denom_2" + col]

tb = tb.drop(columns=["pcnt_pos_1" + col, "pcnt_pos_2" + col, "pcnt_pos_3" + col])
tb = tb.drop(columns=["denom_1" + col, "denom_2" + col, "denom_3" + col])
# tb = tb.drop(columns=["pcnt_pos_1" + col, "pcnt_pos_2" + col, "pcnt_pos_3" + col])
# tb = tb.drop(columns=["denom_1" + col, "denom_2" + col, "denom_3" + col])

# Replace inf with NAs
tb["pcnt_pos" + col] = tb["pcnt_pos" + col].replace([np.inf, -np.inf], np.nan)
Expand Down
14 changes: 7 additions & 7 deletions etl/steps/data/garden/who/latest/flunet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,16 +221,16 @@ def calculate_percent_positive(df: pd.DataFrame, surveillance_cols: list[str]) -
"inf_negative" + col,
] = np.nan

df["pcnt_pos_1" + col] = (df["inf_all" + col] / (df["inf_all" + col] + df["inf_negative" + col])) * 100
df["pcnt_pos_2" + col] = (df["inf_all" + col] / df["spec_processed_nb" + col]) * 100
df["pcnt_pos_3" + col] = (df["inf_all" + col] / df["spec_received_nb" + col]) * 100
df["pcnt_pos" + col] = (df["inf_all" + col] / (df["inf_all" + col] + df["inf_negative" + col])) * 100
# df["pcnt_pos_2" + col] = (df["inf_all" + col] / df["spec_processed_nb" + col]) * 100
# df["pcnt_pos_3" + col] = (df["inf_all" + col] / df["spec_received_nb" + col]) * 100

# hierachically fill the 'pcnt_pos' column with values from the columns described above in order of preference: 1->2->3
df["pcnt_pos" + col] = df["pcnt_pos_1" + col]
df["pcnt_pos" + col] = df["pcnt_pos" + col].fillna(df["pcnt_pos_2" + col])
df["pcnt_pos" + col] = df["pcnt_pos" + col].fillna(df["pcnt_pos_3" + col])
df["pcnt_pos" + col] = df["pcnt_pos" + col]
# df["pcnt_pos" + col] = df["pcnt_pos" + col].fillna(df["pcnt_pos_2" + col])
# df["pcnt_pos" + col] = df["pcnt_pos" + col].fillna(df["pcnt_pos_3" + col])

df = df.drop(columns=["pcnt_pos_1" + col, "pcnt_pos_2" + col, "pcnt_pos_3" + col])
# df = df.drop(columns=["pcnt_pos_1" + col, "pcnt_pos_2" + col, "pcnt_pos_3" + col])

# Drop rows where pcnt_pos is >100
df.loc[df["pcnt_pos" + col] > 100, "pcnt_pos" + col] = np.nan
Expand Down
Loading