diff --git a/.gitignore b/.gitignore
index 95b5515..b2e81fc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -175,3 +175,6 @@ Rscripts/
# Development
dev
+
+# Deployment
+deployments.txt
diff --git a/Dockerfile b/Dockerfile
index 345f36e..89d5e92 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -33,4 +33,5 @@ RUN uv pip install -e .
EXPOSE 80
# Start the server
-CMD ["uv", "run", "streamlit", "run", "hydroshift/streamlit_app.py", "--server.port=80", "--server.address=0.0.0.0", "--server.headless=true"]
+CMD uv run hydroshift/add_analytics.py && uv run streamlit run hydroshift/streamlit_app.py \
+ --server.port=80 --server.address=0.0.0.0 --server.headless=true
diff --git a/docker-compose.yml b/docker-compose.yml
index 1787a17..e27a8ed 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -8,7 +8,14 @@ services:
restart: unless-stopped
mem_limit: 4GB
mem_reservation: 2GB
-
+ stdin_open: true
+ labels:
+ - 'traefik.enable=true'
+ - 'traefik.http.routers.client.rule=Host(`${PROD_APP_HOST}`)'
+ - 'traefik.http.routers.client.tls=true'
+ - 'traefik.http.routers.client.tls.certresolver=letsencrypt'
+ - 'traefik.docker.network=hydroshift_hydroshift'
+ - 'traefik.http.routers.static.middlewares=secHeaders@file'
networks:
hydroshift:
driver: bridge
diff --git a/hydroshift/__init__.py b/hydroshift/__init__.py
index b3f4756..ae73625 100644
--- a/hydroshift/__init__.py
+++ b/hydroshift/__init__.py
@@ -1 +1 @@
-__version__ = "0.1.2"
+__version__ = "0.1.3"
diff --git a/hydroshift/_pages/__init__.py b/hydroshift/_pages/__init__.py
index 2719f4e..200b338 100644
--- a/hydroshift/_pages/__init__.py
+++ b/hydroshift/_pages/__init__.py
@@ -1,3 +1,4 @@
-from hydroshift._pages.changepoint import changepoint
-from hydroshift._pages.homepage import homepage, reset_homepage
-from hydroshift._pages.summary import summary
+from hydroshift._pages.changepoint import changepoint as changepoint
+from hydroshift._pages.homepage import homepage as homepage
+from hydroshift._pages.homepage import reset_homepage as reset_homepage
+from hydroshift._pages.summary import summary as summary
diff --git a/hydroshift/_pages/changepoint.py b/hydroshift/_pages/changepoint.py
index 1768ddd..f5d1bc2 100644
--- a/hydroshift/_pages/changepoint.py
+++ b/hydroshift/_pages/changepoint.py
@@ -72,9 +72,7 @@ def get_change_windows(self, max_dist: float = 10) -> tuple:
current_group_tests = set(test_dict[dates[0]])
for i in range(1, len(dates)):
- if (
- (dates[i] - current_group[-1]).days / 365
- ) < max_dist: # 10 years in days
+ if ((dates[i] - current_group[-1]).days / 365) < max_dist: # 10 years in days
current_group.append(dates[i])
current_group_tests = current_group_tests.union(test_dict[dates[i]])
else:
@@ -93,12 +91,7 @@ def get_max_pvalue(self) -> tuple[float, int]:
"""Get the minimum p value where all tests agree and count how often that occurred."""
all_tests = self.pval_df.fillna(1).max(axis=1).to_frame(name="pval")
all_tests["run"] = ((all_tests != all_tests.shift(1)) * 1).cumsum()
- for ind, r in (
- all_tests.groupby("pval")
- .agg({"run": pd.Series.nunique})
- .sort_index()
- .iterrows()
- ):
+ for ind, r in all_tests.groupby("pval").agg({"run": pd.Series.nunique}).sort_index().iterrows():
if r.run > 0:
min_p = ind
count = r.run
@@ -127,9 +120,7 @@ def ffa_png(self):
@property
def cp_df(self):
"""Get a dataframe representing changepoints identified in the streaming analysis."""
- cpa_df = pd.DataFrame.from_dict(
- self.cp_dict, orient="index", columns=["Tests Identifying Change"]
- )
+ cpa_df = pd.DataFrame.from_dict(self.cp_dict, orient="index", columns=["Tests Identifying Change"])
cpa_df.index = cpa_df.index.date
return cpa_df
@@ -184,9 +175,7 @@ def results_text(self) -> str:
"plural": p_count > 1,
"len_cp": len(self.cp_dict),
"len_cp_str": num_2_word(len(self.cp_dict)),
- "test_count": num_2_word(
- len(self.cp_dict[next(iter(self.cp_dict))].split(","))
- ),
+ "test_count": num_2_word(len(self.cp_dict[next(iter(self.cp_dict))].split(","))),
"grp_count": num_2_word(len(groups)),
"plural_2": len(groups) > 0,
}
@@ -222,9 +211,7 @@ def word_data(self) -> BytesIO:
document.add_heading("Modified flood frequency analysis", level=2)
self.add_markdown_to_doc(document, self.ffa_text)
document.add_picture(self.ffa_png, width=Inches(6.5))
- self.add_markdown_to_doc(
- document, "**Figure 2.** Modified flood frequency analysis."
- )
+ self.add_markdown_to_doc(document, "**Figure 2.** Modified flood frequency analysis.")
self.add_markdown_to_doc(document, "**Table 2.** Modified flood quantiles.")
self.add_table_from_df(self.ffa_df, document, index_name="Regime Period")
@@ -235,9 +222,7 @@ def word_data(self) -> BytesIO:
document.save(out)
return out
- def add_table_from_df(
- self, df: pd.DataFrame, document: Document, index_name: str = None
- ):
+ def add_table_from_df(self, df: pd.DataFrame, document: Document, index_name: str = None):
if index_name is not None:
df = df.copy()
cols = df.columns
@@ -269,10 +254,12 @@ def validate_data(self):
# Validate
if data is None:
- return False, "Unable to retrieve data."
+ return False, "Unable to retrieve data."
elif len(data) < st.session_state.burn_in:
st.session_state.valid_data = False
- return False, "Not enough peaks available for analysis. {} peaks found, but burn-in length was {}".format(len(data["peak_va"]), st.session_state.burn_in)
+ return False, "Not enough peaks available for analysis. {} peaks found, but burn-in length was {}".format(
+ len(data["peak_va"]), st.session_state.burn_in
+ )
else:
return True, None
@@ -336,9 +323,7 @@ def make_sidebar():
# Make data editor. Unique key allows for refreshing
if "data_editor_key" not in st.session_state:
refresh_data_editor()
- start_config = st.column_config.DateColumn(
- "Regime Start", format="D/M/YYYY"
- )
+ start_config = st.column_config.DateColumn("Regime Start", format="D/M/YYYY")
end_config = st.column_config.DateColumn("Regime End", format="D/M/YYYY")
st.data_editor(
init_data,
@@ -351,13 +336,12 @@ def make_sidebar():
st.divider()
write_template("data_sources_side_bar.html")
+
def run_analysis():
"""Run the change point model analysis."""
cpa = st.session_state.changepoint
cpa.pval_df = get_pvalues(cpa.gage.ams)
- cpa.cp_dict = get_changepoints(
- cpa.gage.ams, st.session_state.arlo_slider, st.session_state.burn_in
- )
+ cpa.cp_dict = get_changepoints(cpa.gage.ams, st.session_state.arlo_slider, st.session_state.burn_in)
@st.cache_data(max_entries=MAX_CACHE_ENTRIES)
@@ -392,7 +376,7 @@ def ffa_analysis(data: pd.DataFrame, regimes: list):
if "Regime Start" in r and "Regime End" in r:
sub = data.loc[r["Regime Start"] : r["Regime End"]].copy()
peaks = sub["peak_va"].values
- label = f'{r["Regime Start"]} - {r["Regime End"]}'
+ label = f"{r['Regime Start']} - {r['Regime End']}"
lp3 = LP3Analysis(
st.session_state.gage_id,
peaks,
@@ -464,10 +448,7 @@ def make_body():
def warnings():
"""Print warnings on data validity etc."""
- if (
- st.session_state.changepoint.gage.ams is not None
- and "peak_va" in st.session_state.changepoint.gage.ams.columns
- ):
+ if st.session_state.changepoint.gage.ams is not None and "peak_va" in st.session_state.changepoint.gage.ams.columns:
if st.session_state.changepoint.gage.missing_dates_ams:
st.warning(
"Missing {} dates between {} and {}".format(
diff --git a/hydroshift/_pages/homepage.py b/hydroshift/_pages/homepage.py
index f28ee45..a77c2c8 100644
--- a/hydroshift/_pages/homepage.py
+++ b/hydroshift/_pages/homepage.py
@@ -1,24 +1,11 @@
import streamlit as st
+
from hydroshift._pages import summary
from hydroshift.consts import DEFAULT_GAGE
from hydroshift.utils.jinja import write_template
-
-def homepage():
- """Landing page for app."""
- # st.session_state["gage_id"] = None
- st.set_page_config(layout="centered", initial_sidebar_state ="collapsed")
-
- st.markdown(
- """
+PAGE_CSS = """
- """,
+ """
+
+
+def homepage():
+ """Landing page for app."""
+ st.set_page_config(layout="centered", initial_sidebar_state="collapsed")
+
+ st.markdown(
+ PAGE_CSS,
unsafe_allow_html=True,
)
- # --- Centered content ---
- with st.container(horizontal_alignment ="center"):
+ with st.container(horizontal_alignment="center"):
st.title("HydroShift")
- with st.container(horizontal=True, horizontal_alignment ="center"):
+ with st.container(horizontal=True, horizontal_alignment="center"):
st.image("hydroshift/images/logo_base.png", width=400)
st.subheader("USGS Streamflow Change Detection Tool")
@@ -55,7 +77,7 @@ def homepage():
gage_input = st.text_input("Enter a USGS Gage Number:", placeholder="e.g., 01646500")
- with st.container(horizontal=True, horizontal_alignment ="center"):
+ with st.container(horizontal=True, horizontal_alignment="center"):
submit = st.button("Submit")
demo = st.button("Use Demo Data")
@@ -70,6 +92,7 @@ def homepage():
write_template("footer.html")
+
def reset_homepage():
st.session_state["gage_id"] = None
st.rerun()
diff --git a/hydroshift/_pages/summary.py b/hydroshift/_pages/summary.py
index 41eae26..70fe791 100644
--- a/hydroshift/_pages/summary.py
+++ b/hydroshift/_pages/summary.py
@@ -1,6 +1,5 @@
-from datetime import date
import datetime
-import time
+from datetime import date
import folium
import streamlit as st
@@ -137,14 +136,13 @@ def section_monthly_mean(gage: Gage):
"Log-Pearson III (LP3) Analysis": section_lp3,
"AMS Seasonal Ranking": section_ams_seasonal,
"Daily Mean Streamflow": section_daily_mean,
- "Monthly Mean Streamflow": section_monthly_mean
+ "Monthly Mean Streamflow": section_monthly_mean,
}
-
def summary():
"""Display summary plots for various timeseries associated with this gage."""
- st.set_page_config(page_title="Gage Summary", layout="wide", initial_sidebar_state ="auto")
+ st.set_page_config(page_title="Gage Summary", layout="wide", initial_sidebar_state="auto")
# Sidebar for input
with st.sidebar:
@@ -180,7 +178,10 @@ def summary():
# Display site metadata
st.subheader("Site Information")
write_template("site_summary.md", gage.site_data)
- st.link_button("Go to USGS", f'https://waterdata.usgs.gov/monitoring-location/USGS-{st.session_state["gage_id"]}/')
+ st.link_button(
+ "Go to USGS",
+ f"https://waterdata.usgs.gov/monitoring-location/USGS-{st.session_state['gage_id']}/",
+ )
with st.spinner():
gage.raise_warnings()
diff --git a/hydroshift/add_analytics.py b/hydroshift/add_analytics.py
new file mode 100644
index 0000000..227b347
--- /dev/null
+++ b/hydroshift/add_analytics.py
@@ -0,0 +1,34 @@
+import os
+from bs4 import BeautifulSoup
+import pathlib
+import shutil
+import streamlit as st
+
+GA_ID = "google_analytics"
+GA_TAG = os.getenv("GA_TAG", "") # pull tag from env, fallback to empty
+GA_SCRIPT = f"""
+
+
+
+"""
+
+def inject_ga():
+ index_path = pathlib.Path(st.__file__).parent / "static" / "index.html"
+ soup = BeautifulSoup(index_path.read_text(), features="html.parser")
+ if not soup.find(id=GA_ID):
+ bck_index = index_path.with_suffix('.bck')
+ if bck_index.exists():
+ shutil.copy(bck_index, index_path)
+ else:
+ shutil.copy(index_path, bck_index)
+ html = str(soup)
+ new_html = html.replace('', '\n' + GA_SCRIPT)
+ index_path.write_text(new_html)
+
+inject_ga()
diff --git a/hydroshift/logging.py b/hydroshift/app_logging.py
similarity index 93%
rename from hydroshift/logging.py
rename to hydroshift/app_logging.py
index ad42744..1d53665 100644
--- a/hydroshift/logging.py
+++ b/hydroshift/app_logging.py
@@ -1,8 +1,8 @@
# logging_config.py
import logging
import logging.handlers
-from pathlib import Path
import sys
+from pathlib import Path
def handle_uncaught(exc_type, exc_value, exc_traceback):
@@ -18,7 +18,7 @@ def setup_logging(log_dir: str = "logs", log_level: int = logging.INFO, log_file
log_path = Path(log_dir) / log_file
# Establish format
- log_format = ("%(asctime)s | %(levelname)-8s | %(name)s.%(funcName)s:%(lineno)d | %(message)s")
+ log_format = "%(asctime)s | %(levelname)-8s | %(name)s.%(funcName)s:%(lineno)d | %(message)s"
formatter = logging.Formatter(log_format, "%Y-%m-%d %H:%M:%S")
# Establish global settings
diff --git a/hydroshift/consts.py b/hydroshift/consts.py
index 751e56a..a092df6 100644
--- a/hydroshift/consts.py
+++ b/hydroshift/consts.py
@@ -1,4 +1,5 @@
"""Shared variables."""
+
# Performance
MAX_CACHE_ENTRIES = 25
@@ -60,6 +61,7 @@
"C": "All or part of the record affected by Urbanization, Mining, Agricultural changes, Channelization, or other",
}
+
### IMAGES ###
def svg2text(path: str) -> str:
with open(path, "r") as f:
@@ -67,6 +69,8 @@ def svg2text(path: str) -> str:
if svg.startswith("", 1)[1]
return svg.strip()
+
+
GITHUB_SVG = svg2text("hydroshift/images/github_logo.svg")
DEWBERRY_SVG = svg2text("hydroshift/images/dewberry_logo.svg")
MAIL_SVG = svg2text("hydroshift/images/mail_logo.svg")
diff --git a/hydroshift/rserver/start_r_server.py b/hydroshift/rserver/start_r_server.py
index e0cd353..e7df0ab 100644
--- a/hydroshift/rserver/start_r_server.py
+++ b/hydroshift/rserver/start_r_server.py
@@ -7,12 +7,13 @@
import psutil
import requests
+import streamlit as st
from hydroshift.consts import R_SERVER_PORT
-import streamlit as st
logger = logging.getLogger(__name__)
+
def server_running(port: str) -> bool:
"""Check if server is running."""
try:
@@ -30,6 +31,7 @@ def stop_server(pid: int):
logger.info("Stopping server")
psutil.Process(pid).terminate()
+
@st.cache_resource
def start_server():
"""Start an R server."""
diff --git a/hydroshift/streamlit_app.py b/hydroshift/streamlit_app.py
index 5e3d181..6df33de 100644
--- a/hydroshift/streamlit_app.py
+++ b/hydroshift/streamlit_app.py
@@ -1,13 +1,13 @@
import logging
-import sys
import time
+
import streamlit as st
-from session import init_session_state
from PIL import Image
+from hydroshift.session import init_session_state
-from hydroshift._pages import changepoint, homepage, summary, reset_homepage
+from hydroshift._pages import changepoint, homepage, reset_homepage, summary
+from hydroshift.app_logging import setup_logging
-from hydroshift.logging import setup_logging
setup_logging()
logger = logging.getLogger(__name__)
@@ -16,9 +16,10 @@
def navigator():
"""Make sidebar for multi-page navigation."""
time.sleep(0.1)
+
# Define general style
im = Image.open("hydroshift/images/favicon.ico")
- st.set_page_config(page_title="HydroShift",page_icon=im)
+ st.set_page_config(page_title="HydroShift", page_icon=im)
# Initialize state
if "session_id" not in st.session_state:
diff --git a/hydroshift/utils/data_retrieval.py b/hydroshift/utils/data_retrieval.py
index 71c1607..681e13f 100644
--- a/hydroshift/utils/data_retrieval.py
+++ b/hydroshift/utils/data_retrieval.py
@@ -1,7 +1,4 @@
-from functools import cached_property
import logging
-import time
-import traceback
from typing import List
import numpy as np
@@ -12,9 +9,10 @@
from dataretrieval import NoSitesError, nwis
from scipy.stats import genpareto
-from hydroshift.consts import REGULATION_MAP, MAX_CACHE_ENTRIES
+from hydroshift.consts import MAX_CACHE_ENTRIES, REGULATION_MAP
from hydroshift.errors import GageNotFoundException
from hydroshift.utils.common import group_consecutive_years
+
logger = logging.getLogger(__name__)
@@ -37,8 +35,7 @@ def validate_id(idx: str):
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def latitude(self) -> float:
"""Latitude of gage."""
@@ -46,8 +43,7 @@ def latitude(self) -> float:
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def longitude(self) -> float:
"""Longitude of gage."""
@@ -55,8 +51,7 @@ def longitude(self) -> float:
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def elevation(self) -> float:
"""Elevation of gage."""
@@ -64,35 +59,28 @@ def elevation(self) -> float:
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def mean_basin_elevation(self) -> float:
"""Average elevation of gage watershed."""
try:
- row = [
- r for r in self.streamstats["characteristics"] if r["variableTypeID"] == 6
- ] # Get ELEV param
+ row = [r for r in self.streamstats["characteristics"] if r["variableTypeID"] == 6] # Get ELEV param
return row[0]["value"]
except (KeyError, IndexError):
return None
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def streamstats(self) -> pd.DataFrame:
"""Load AMS for this site."""
- r = requests.get(
- f"https://streamstats.usgs.gov/gagestatsservices/stations/{self.gage_id}"
- )
+ r = requests.get(f"https://streamstats.usgs.gov/gagestatsservices/stations/{self.gage_id}")
return r.json()
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def ams(self) -> pd.DataFrame:
"""Load AMS for this site."""
@@ -110,16 +98,14 @@ def missing_dates_ams(self) -> list:
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def flow_stats(self) -> pd.DataFrame:
"""Load flow statistics for this site."""
return get_flow_stats(self.gage_id)
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def get_daily_values(self, start_date: str, end_date: str) -> pd.DataFrame:
"""Load daily mean discharge for this site."""
@@ -131,8 +117,7 @@ def missing_dates_daily_values(self, start_date: str, end_date: str) -> list:
@property
@st.cache_data(
- hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)},
- max_entries=MAX_CACHE_ENTRIES
+ hash_funcs={"hydroshift.utils.data_retrieval.Gage": lambda x: hash(x.gage_id)}, max_entries=MAX_CACHE_ENTRIES
)
def monthly_values(self) -> pd.DataFrame:
"""Load monthly mean discharge for this site."""
@@ -161,22 +146,16 @@ def get_regulation_summary(self, major_codes=["3", "9"]) -> List[str]:
code_key = code_str
if code_key in REGULATION_MAP:
- regulation_years.setdefault(code_key, set()).add(
- row["water_year"]
- )
+ regulation_years.setdefault(code_key, set()).add(row["water_year"])
results = {"major": [], "minor": []}
for code, years in regulation_years.items():
grouped_year_ranges = group_consecutive_years(sorted(years))
formatted_ranges = ", ".join(grouped_year_ranges)
if code in major_codes:
- results["major"].append(
- f"{REGULATION_MAP[code]} for water years {formatted_ranges}"
- )
+ results["major"].append(f"{REGULATION_MAP[code]} for water years {formatted_ranges}")
else:
- results["minor"].append(
- f"{REGULATION_MAP[code]} for water years {formatted_ranges}"
- )
+ results["minor"].append(f"{REGULATION_MAP[code]} for water years {formatted_ranges}")
return results
@@ -218,9 +197,7 @@ def regional_skew(self) -> float:
if val == 9999: # California Eq. from USGS SIR 2010-5260 NL-ELEV eq
if self.mean_basin_elevation is None:
return None
- val = (0 - 0.62) + 1.3 * (
- 1 - np.exp(0 - ((self.mean_basin_elevation) / 6500) ** 2)
- )
+ val = (0 - 0.62) + 1.3 * (1 - np.exp(0 - ((self.mean_basin_elevation) / 6500) ** 2))
return val
@property
@@ -267,7 +244,6 @@ def available_plots(self) -> list[str]:
return plots
-
@st.cache_data(max_entries=MAX_CACHE_ENTRIES)
def get_ams(gage_id):
"""Fetches Annual Maximum Series (AMS) peak flow data for a given gage."""
@@ -319,11 +295,12 @@ def load_site_data(gage_number: str) -> dict:
"alt_datum_cd": resp["alt_datum_cd"].iloc[0],
}
+
@st.cache_data(max_entries=MAX_CACHE_ENTRIES)
def get_site_catalog(gage_number: str) -> dict:
"""Query NWIS for site information"""
try:
- df = nwis.what_sites(sites=gage_number, seriesCatalogOutput='true', ssl_check=True)[0]
+ df = nwis.what_sites(sites=gage_number, seriesCatalogOutput="true", ssl_check=True)[0]
except Exception as e:
logger.error("Error querying site: %s", e, exc_info=True)
return df
@@ -333,7 +310,7 @@ def get_site_catalog(gage_number: str) -> dict:
def get_daily_values(gage_id, start_date, end_date):
"""Fetches mean daily flow values for a given gage."""
try:
- dv = nwis.get_dv(gage_id, start_date, end_date, ssl_check=True, parameterCd ="00060")[0]
+ dv = nwis.get_dv(gage_id, start_date, end_date, ssl_check=True, parameterCd="00060")[0]
except Exception:
logger.debug(f"Daily Values could not be found for gage_id: {gage_id}")
return None
@@ -345,7 +322,7 @@ def get_daily_values(gage_id, start_date, end_date):
def get_monthly_values(gage_id):
"""Fetches mean monthly flow values for a given gage and assigns a datetime column based on the year and month."""
try:
- mv = nwis.get_stats(gage_id, statReportType="monthly", ssl_check=True, parameterCd = "00060")[0]
+ mv = nwis.get_stats(gage_id, statReportType="monthly", ssl_check=True, parameterCd="00060")[0]
except Exception:
logger.debug(f"Monthly Values could not be found for gage_id: {gage_id}")
return None
@@ -379,9 +356,7 @@ def check_missing_dates(df, freq):
elif freq == "monthly":
df["date"] = pd.to_datetime(df["date"])
- full_range = pd.date_range(
- start=df["date"].min(), end=df["date"].max(), freq="MS"
- )
+ full_range = pd.date_range(start=df["date"].min(), end=df["date"].max(), freq="MS")
elif freq == "water_year":
if not isinstance(df.index, pd.DatetimeIndex):
@@ -389,9 +364,7 @@ def check_missing_dates(df, freq):
df["water_year"] = df.index.year.where(df.index.month < 10, df.index.year + 1)
- full_water_years = set(
- range(df["water_year"].min(), df["water_year"].max() + 1)
- )
+ full_water_years = set(range(df["water_year"].min(), df["water_year"].max() + 1))
existing_water_years = set(df["water_year"])
missing_years = sorted(full_water_years - existing_water_years)
@@ -423,15 +396,11 @@ def fake_ams() -> pd.DataFrame:
rvs = np.concatenate(rvs, axis=0)
dates = pd.date_range(start="1900-01-01", periods=len(rvs), freq="YE")
water_year = dates.year
- df = pd.DataFrame(
- {"datetime": dates, "peak_va": rvs, "water_year": water_year}
- ).set_index("datetime")
+ df = pd.DataFrame({"datetime": dates, "peak_va": rvs, "water_year": water_year}).set_index("datetime")
return df
@st.cache_resource
def get_skew_raster():
"""Load the skew raster into memory."""
- return rasterio.open(
- __file__.replace("utils/data_retrieval.py", "data/skewmap_4326.tif")
- )
+ return rasterio.open(__file__.replace("utils/data_retrieval.py", "data/skewmap_4326.tif"))
diff --git a/hydroshift/utils/ffa.py b/hydroshift/utils/ffa.py
index 381b568..3b69d4c 100644
--- a/hydroshift/utils/ffa.py
+++ b/hydroshift/utils/ffa.py
@@ -18,9 +18,7 @@ class LP3Analysis:
use_map_skew: bool = False
est_method: str = "MLE"
label: str = ""
- return_periods: List[str] = field(
- default_factory=lambda: [1.1, 2, 5, 10, 25, 50, 100, 500]
- )
+ return_periods: List[str] = field(default_factory=lambda: [1.1, 2, 5, 10, 25, 50, 100, 500])
# TODO: Add california equation. Likely best to subclass this.
diff --git a/hydroshift/utils/plots.py b/hydroshift/utils/plots.py
index 401ca31..07ff532 100644
--- a/hydroshift/utils/plots.py
+++ b/hydroshift/utils/plots.py
@@ -89,7 +89,7 @@ def plot_flow_stats(stats_df, gage_id):
"""Plot Flow Statistics using Plotly with month-abbreviation x-axis labels."""
# Ensure data is sorted
# Create a datetime column
- p_cols = ['p05_va', 'p10_va', 'p20_va', 'p25_va', 'p50_va', 'p75_va', 'p80_va', 'p90_va', 'p95_va']
+ p_cols = ["p05_va", "p10_va", "p20_va", "p25_va", "p50_va", "p75_va", "p80_va", "p90_va", "p95_va"]
stats_df[p_cols] = stats_df[p_cols].ffill()
stats_df[p_cols] = stats_df[p_cols].fillna(0)
stats_df["date"] = pd.to_datetime(
@@ -229,9 +229,7 @@ def plot_lp3(data: LP3Analysis | list[LP3Analysis]):
)
# Formatting
- return_periods = [
- int(i) if i.is_integer() else round(i, 1) for i in i.return_periods
- ]
+ return_periods = [int(i) if i.is_integer() else round(i, 1) for i in i.return_periods]
if i.use_map_skew:
skew_txt = ""
else:
diff --git a/pyproject.toml b/pyproject.toml
index 5208099..340ef1a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -27,3 +27,14 @@ dependencies = [
[tool.setuptools.packages.find]
include = ["hydroshift*"]
namespaces = false
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = ["F401", "I001"] # unused imports + import sorting
+
+[dependency-groups]
+dev = [
+ "ruff>=0.13.1",
+]
diff --git a/uv.lock b/uv.lock
index ef7d559..5896b86 100644
--- a/uv.lock
+++ b/uv.lock
@@ -625,6 +625,11 @@ dependencies = [
{ name = "streamlit-folium" },
]
+[package.dev-dependencies]
+dev = [
+ { name = "ruff" },
+]
+
[package.metadata]
requires-dist = [
{ name = "dataretrieval", specifier = "==1.0.11" },
@@ -646,6 +651,9 @@ requires-dist = [
{ name = "streamlit-folium", specifier = "==0.24.0" },
]
+[package.metadata.requires-dev]
+dev = [{ name = "ruff", specifier = ">=0.13.1" }]
+
[[package]]
name = "idna"
version = "3.10"
@@ -1923,6 +1931,32 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/32/7d/97119da51cb1dd3f2f3c0805f155a3aa4a95fa44fe7d78ae15e69edf4f34/rpds_py-0.27.1-cp314-cp314t-win_amd64.whl", hash = "sha256:6567d2bb951e21232c2f660c24cf3470bb96de56cdcb3f071a83feeaff8a2772", size = 230097, upload-time = "2025-08-27T12:15:03.961Z" },
]
+[[package]]
+name = "ruff"
+version = "0.13.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ab/33/c8e89216845615d14d2d42ba2bee404e7206a8db782f33400754f3799f05/ruff-0.13.1.tar.gz", hash = "sha256:88074c3849087f153d4bb22e92243ad4c1b366d7055f98726bc19aa08dc12d51", size = 5397987, upload-time = "2025-09-18T19:52:44.33Z" }
+wheels = [
+ { url = "https://files.pythonhosted.org/packages/f3/41/ca37e340938f45cfb8557a97a5c347e718ef34702546b174e5300dbb1f28/ruff-0.13.1-py3-none-linux_armv6l.whl", hash = "sha256:b2abff595cc3cbfa55e509d89439b5a09a6ee3c252d92020bd2de240836cf45b", size = 12304308, upload-time = "2025-09-18T19:51:56.253Z" },
+ { url = "https://files.pythonhosted.org/packages/ff/84/ba378ef4129415066c3e1c80d84e539a0d52feb250685091f874804f28af/ruff-0.13.1-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:4ee9f4249bf7f8bb3984c41bfaf6a658162cdb1b22e3103eabc7dd1dc5579334", size = 12937258, upload-time = "2025-09-18T19:52:00.184Z" },
+ { url = "https://files.pythonhosted.org/packages/8d/b6/ec5e4559ae0ad955515c176910d6d7c93edcbc0ed1a3195a41179c58431d/ruff-0.13.1-py3-none-macosx_11_0_arm64.whl", hash = "sha256:5c5da4af5f6418c07d75e6f3224e08147441f5d1eac2e6ce10dcce5e616a3bae", size = 12214554, upload-time = "2025-09-18T19:52:02.753Z" },
+ { url = "https://files.pythonhosted.org/packages/70/d6/cb3e3b4f03b9b0c4d4d8f06126d34b3394f6b4d764912fe80a1300696ef6/ruff-0.13.1-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:80524f84a01355a59a93cef98d804e2137639823bcee2931f5028e71134a954e", size = 12448181, upload-time = "2025-09-18T19:52:05.279Z" },
+ { url = "https://files.pythonhosted.org/packages/d2/ea/bf60cb46d7ade706a246cd3fb99e4cfe854efa3dfbe530d049c684da24ff/ruff-0.13.1-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ff7f5ce8d7988767dd46a148192a14d0f48d1baea733f055d9064875c7d50389", size = 12104599, upload-time = "2025-09-18T19:52:07.497Z" },
+ { url = "https://files.pythonhosted.org/packages/2d/3e/05f72f4c3d3a69e65d55a13e1dd1ade76c106d8546e7e54501d31f1dc54a/ruff-0.13.1-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c55d84715061f8b05469cdc9a446aa6c7294cd4bd55e86a89e572dba14374f8c", size = 13791178, upload-time = "2025-09-18T19:52:10.189Z" },
+ { url = "https://files.pythonhosted.org/packages/81/e7/01b1fc403dd45d6cfe600725270ecc6a8f8a48a55bc6521ad820ed3ceaf8/ruff-0.13.1-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:ac57fed932d90fa1624c946dc67a0a3388d65a7edc7d2d8e4ca7bddaa789b3b0", size = 14814474, upload-time = "2025-09-18T19:52:12.866Z" },
+ { url = "https://files.pythonhosted.org/packages/fa/92/d9e183d4ed6185a8df2ce9faa3f22e80e95b5f88d9cc3d86a6d94331da3f/ruff-0.13.1-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c366a71d5b4f41f86a008694f7a0d75fe409ec298685ff72dc882f882d532e36", size = 14217531, upload-time = "2025-09-18T19:52:15.245Z" },
+ { url = "https://files.pythonhosted.org/packages/3b/4a/6ddb1b11d60888be224d721e01bdd2d81faaf1720592858ab8bac3600466/ruff-0.13.1-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4ea9d1b5ad3e7a83ee8ebb1229c33e5fe771e833d6d3dcfca7b77d95b060d38", size = 13265267, upload-time = "2025-09-18T19:52:17.649Z" },
+ { url = "https://files.pythonhosted.org/packages/81/98/3f1d18a8d9ea33ef2ad508f0417fcb182c99b23258ec5e53d15db8289809/ruff-0.13.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b0f70202996055b555d3d74b626406476cc692f37b13bac8828acff058c9966a", size = 13243120, upload-time = "2025-09-18T19:52:20.332Z" },
+ { url = "https://files.pythonhosted.org/packages/8d/86/b6ce62ce9c12765fa6c65078d1938d2490b2b1d9273d0de384952b43c490/ruff-0.13.1-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:f8cff7a105dad631085d9505b491db33848007d6b487c3c1979dd8d9b2963783", size = 13443084, upload-time = "2025-09-18T19:52:23.032Z" },
+ { url = "https://files.pythonhosted.org/packages/a1/6e/af7943466a41338d04503fb5a81b2fd07251bd272f546622e5b1599a7976/ruff-0.13.1-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:9761e84255443316a258dd7dfbd9bfb59c756e52237ed42494917b2577697c6a", size = 12295105, upload-time = "2025-09-18T19:52:25.263Z" },
+ { url = "https://files.pythonhosted.org/packages/3f/97/0249b9a24f0f3ebd12f007e81c87cec6d311de566885e9309fcbac5b24cc/ruff-0.13.1-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:3d376a88c3102ef228b102211ef4a6d13df330cb0f5ca56fdac04ccec2a99700", size = 12072284, upload-time = "2025-09-18T19:52:27.478Z" },
+ { url = "https://files.pythonhosted.org/packages/f6/85/0b64693b2c99d62ae65236ef74508ba39c3febd01466ef7f354885e5050c/ruff-0.13.1-py3-none-musllinux_1_2_i686.whl", hash = "sha256:cbefd60082b517a82c6ec8836989775ac05f8991715d228b3c1d86ccc7df7dae", size = 12970314, upload-time = "2025-09-18T19:52:30.212Z" },
+ { url = "https://files.pythonhosted.org/packages/96/fc/342e9f28179915d28b3747b7654f932ca472afbf7090fc0c4011e802f494/ruff-0.13.1-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:dd16b9a5a499fe73f3c2ef09a7885cb1d97058614d601809d37c422ed1525317", size = 13422360, upload-time = "2025-09-18T19:52:32.676Z" },
+ { url = "https://files.pythonhosted.org/packages/37/54/6177a0dc10bce6f43e392a2192e6018755473283d0cf43cc7e6afc182aea/ruff-0.13.1-py3-none-win32.whl", hash = "sha256:55e9efa692d7cb18580279f1fbb525146adc401f40735edf0aaeabd93099f9a0", size = 12178448, upload-time = "2025-09-18T19:52:35.545Z" },
+ { url = "https://files.pythonhosted.org/packages/64/51/c6a3a33d9938007b8bdc8ca852ecc8d810a407fb513ab08e34af12dc7c24/ruff-0.13.1-py3-none-win_amd64.whl", hash = "sha256:3a3fb595287ee556de947183489f636b9f76a72f0fa9c028bdcabf5bab2cc5e5", size = 13286458, upload-time = "2025-09-18T19:52:38.198Z" },
+ { url = "https://files.pythonhosted.org/packages/fd/04/afc078a12cf68592345b1e2d6ecdff837d286bac023d7a22c54c7a698c5b/ruff-0.13.1-py3-none-win_arm64.whl", hash = "sha256:c0bae9ffd92d54e03c2bf266f466da0a65e145f298ee5b5846ed435f6a00518a", size = 12437893, upload-time = "2025-09-18T19:52:41.283Z" },
+]
+
[[package]]
name = "scipy"
version = "1.15.2"