Skip to content

Commit

Permalink
Loading
Loading status checks…
Merge pull request #60 from jvivian/jvivian/issue55
Browse files Browse the repository at this point in the history 
Add raw data to filtered factors and add unittest
@jvivian
jvivian authored Mar 6, 2024

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode
2 parents 00e853a + 031f048 commit cde822a
Showing 7 changed files with 279 additions and 93 deletions.
134 changes: 68 additions & 66 deletions coverage.xml
View file
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
<?xml version="1.0" ?>
<coverage version="7.3.1" timestamp="1709534576492" lines-valid="191" lines-covered="190" line-rate="0.9948" branches-valid="66" branches-covered="63" branch-rate="0.9545" complexity="0">
<!-- Generated by coverage.py: https://coverage.readthedocs.io/en/7.3.1 -->
<coverage version="7.4.3" timestamp="1709686796870" lines-valid="193" lines-covered="188" line-rate="0.9741" branches-valid="66" branches-covered="62" branch-rate="0.9394" complexity="0">
<!-- Generated by coverage.py: https://coverage.readthedocs.io/en/7.4.3 -->
<!-- Based on https://raw.githubusercontent.com/cobertura/web/master/htdocs/xml/coverage-04.dtd -->
<sources>
<source>/home/jvivian/covid19-drDFM/covid19_drdfm</source>
</sources>
<packages>
<package name="." line-rate="0.9948" branch-rate="0.9545" complexity="0">
<package name="." line-rate="0.9741" branch-rate="0.9394" complexity="0">
<classes>
<class name="cli.py" filename="cli.py" complexity="0" line-rate="1" branch-rate="1">
<methods/>
@@ -47,54 +47,54 @@
<line number="153" hits="1"/>
</lines>
</class>
<class name="dfm.py" filename="dfm.py" complexity="0" line-rate="1" branch-rate="0.95">
<class name="dfm.py" filename="dfm.py" complexity="0" line-rate="0.9394" branch-rate="0.9">
<methods/>
<lines>
<line number="7" hits="1"/>
<line number="8" hits="1"/>
<line number="9" hits="1"/>
<line number="10" hits="1"/>
<line number="11" hits="1"/>
<line number="12" hits="1"/>
<line number="13" hits="1"/>
<line number="14" hits="1"/>
<line number="15" hits="1"/>
<line number="16" hits="1"/>
<line number="17" hits="1"/>
<line number="20" hits="1"/>
<line number="22" hits="1"/>
<line number="25" hits="1"/>
<line number="19" hits="1"/>
<line number="21" hits="1"/>
<line number="24" hits="1"/>
<line number="34" hits="1"/>
<line number="35" hits="1"/>
<line number="36" hits="1"/>
<line number="37" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="36" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="37" hits="1"/>
<line number="38" hits="1"/>
<line number="39" hits="1"/>
<line number="42" hits="1"/>
<line number="51" hits="1"/>
<line number="52" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="41" hits="1"/>
<line number="50" hits="1"/>
<line number="51" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="52" hits="1"/>
<line number="53" hits="1"/>
<line number="54" hits="1"/>
<line number="55" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="56" hits="1"/>
<line number="54" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="55" hits="1"/>
<line number="57" hits="1"/>
<line number="58" hits="1"/>
<line number="59" hits="1"/>
<line number="62" hits="1"/>
<line number="61" hits="1"/>
<line number="80" hits="1"/>
<line number="81" hits="1"/>
<line number="82" hits="1"/>
<line number="83" hits="1" branch="true" condition-coverage="50% (1/2)" missing-branches="exit"/>
<line number="84" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="85" hits="1"/>
<line number="82" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="83" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="84" hits="1"/>
<line number="85" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="86" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="87" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="88" hits="1"/>
<line number="87" hits="1"/>
<line number="89" hits="1"/>
<line number="90" hits="1"/>
<line number="91" hits="1"/>
<line number="92" hits="1"/>
<line number="93" hits="1"/>
<line number="94" hits="1"/>
<line number="95" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="96" hits="1"/>
<line number="93" hits="0"/>
<line number="94" hits="0" branch="true" condition-coverage="0% (0/2)" missing-branches="95,96"/>
<line number="95" hits="0"/>
<line number="96" hits="0"/>
<line number="97" hits="1"/>
<line number="98" hits="1"/>
<line number="99" hits="1"/>
<line number="101" hits="1"/>
<line number="102" hits="1"/>
<line number="103" hits="1"/>
<line number="104" hits="1"/>
@@ -114,6 +114,8 @@
<line number="120" hits="1"/>
<line number="121" hits="1"/>
<line number="122" hits="1"/>
<line number="123" hits="1"/>
<line number="124" hits="1"/>
</lines>
</class>
<class name="processing.py" filename="processing.py" complexity="0" line-rate="0.9846" branch-rate="0.9688">
@@ -137,53 +139,53 @@
<line number="36" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="39" hits="1"/>
<line number="46" hits="1"/>
<line number="55" hits="1"/>
<line number="62" hits="1"/>
<line number="65" hits="1"/>
<line number="79" hits="1"/>
<line number="80" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="81" hits="1"/>
<line number="82" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="83" hits="1"/>
<line number="84" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="85" hits="1"/>
<line number="86" hits="1" branch="true" condition-coverage="50% (1/2)" missing-branches="87"/>
<line number="87" hits="0"/>
<line number="89" hits="1"/>
<line number="92" hits="1"/>
<line number="98" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="56" hits="1"/>
<line number="63" hits="1"/>
<line number="66" hits="1"/>
<line number="80" hits="1"/>
<line number="81" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="82" hits="1"/>
<line number="83" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="84" hits="1"/>
<line number="85" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="86" hits="1"/>
<line number="87" hits="1" branch="true" condition-coverage="50% (1/2)" missing-branches="88"/>
<line number="88" hits="0"/>
<line number="90" hits="1"/>
<line number="93" hits="1"/>
<line number="99" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="102" hits="1"/>
<line number="111" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="122" hits="1"/>
<line number="131" hits="1"/>
<line number="100" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="103" hits="1"/>
<line number="112" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="123" hits="1"/>
<line number="132" hits="1"/>
<line number="133" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="134" hits="1"/>
<line number="133" hits="1"/>
<line number="134" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="135" hits="1"/>
<line number="136" hits="1"/>
<line number="137" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="138" hits="1"/>
<line number="137" hits="1"/>
<line number="138" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="139" hits="1"/>
<line number="142" hits="1"/>
<line number="151" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="152" hits="1"/>
<line number="140" hits="1"/>
<line number="143" hits="1"/>
<line number="152" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="153" hits="1"/>
<line number="156" hits="1"/>
<line number="165" hits="1"/>
<line number="168" hits="1"/>
<line number="181" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="154" hits="1"/>
<line number="157" hits="1"/>
<line number="166" hits="1"/>
<line number="169" hits="1"/>
<line number="182" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="184" hits="1"/>
<line number="183" hits="1" branch="true" condition-coverage="100% (2/2)"/>
<line number="185" hits="1"/>
<line number="188" hits="1"/>
<line number="197" hits="1"/>
<line number="186" hits="1"/>
<line number="189" hits="1"/>
<line number="198" hits="1"/>
<line number="200" hits="1"/>
<line number="199" hits="1"/>
<line number="201" hits="1"/>
<line number="202" hits="1"/>
<line number="203" hits="1"/>
<line number="204" hits="1"/>
<line number="205" hits="1"/>
</lines>
</class>
<class name="results.py" filename="results.py" complexity="0" line-rate="1" branch-rate="0.9167">
10 changes: 6 additions & 4 deletions covid19_drdfm/dfm.py
View file
Original file line number Diff line number Diff line change
@@ -4,7 +4,6 @@
- `c19_dfm run`
"""

from dataclasses import dataclass
from pathlib import Path
from typing import Optional

@@ -14,7 +13,7 @@
from statsmodels.tsa.stattools import adfuller

from covid19_drdfm.constants import DIFF_COLS, FACTORS, LOG_DIFF_COLS
from covid19_drdfm.processing import diff_vars, normalize, get_raw, write
from covid19_drdfm.processing import diff_vars, get_raw, normalize, write


def is_constant(column) -> bool:
@@ -104,7 +103,8 @@ def _save_input(df, state, columns, outdir):
out = outdir / state
out.mkdir(exist_ok=True)
raw = get_raw().query("State == @state")
raw = raw[columns] if columns else raw
raw = raw[columns + ["Time"]] if columns else raw
raw = raw.set_index("Time").loc[df.index]
write(raw, out / "raw.csv")
write(df, (out / "df.xlsx"))
write(df, out / "df.csv")
@@ -118,5 +118,7 @@ def _save_output(df, model, results, state, outdir):
f.write(results.summary().as_csv())
filtered = results.factors["filtered"]
filtered["State"] = state
filtered.index = df.index
raw = pd.read_csv(out / "raw.csv", index_col=0)
filtered.index = raw.index
filtered = filtered.merge(raw, left_index=True, right_index=True)
filtered.to_csv(out / "filtered-factors.csv")
3 changes: 2 additions & 1 deletion covid19_drdfm/processing.py
View file
Original file line number Diff line number Diff line change
@@ -48,6 +48,7 @@ def get_raw() -> pd.DataFrame:
.drop(columns=["Monetary_1_x", "Monetary_11_x"])
.rename(columns={"Monetary_1_y": "Monetary_1", "Monetary_11_y": "Monetary_11"})
.drop(columns=["Proportion", "proportion_vax2", "Pandemic_Response_8", "Distributed"])
.pipe(add_datetime)
.pipe(fix_names)
)

@@ -59,7 +60,7 @@ def get_df() -> pd.DataFrame:
Returns:
pd.DataFrame: The cleaned DataFrame.
"""
return get_raw().pipe(adjust_inflation).pipe(add_datetime).pipe(adjust_pandemic_response)
return get_raw().pipe(adjust_inflation).pipe(adjust_pandemic_response)


def write(df: pd.DataFrame, outpath: Path) -> None:
Loading

0 comments on commit cde822a

Please sign in to comment.