tommylees112

import xarray as xr
from pathlib import Path
from tqdm import tqdm
import xesmf as xe


def convert_to_same_grid(reference_ds: xr.Dataset, ds: xr.Dataset, method: str="nearest_s2d") -> xr.Dataset:
    """ Use xEMSF package to regrid ds to the same grid as reference_ds """
    assert ("lat" in reference_ds.dims) & (
        "lon" in reference_ds.dims

tommylees112

import geopandas as gpd
import xarray as xr
from pathlib import Path
import matplotlib.pyplot as plt


def load_latlon_points(data_dir: Path) -> gpd.GeoSeries:
    static = xr.open_dataset(data_dir / "camels_static.nc")
    d = static[["gauge_lat", "gauge_lon"]].to_dataframe()
    points = gpd.GeoSeries(

tommylees112

tommylees112

conda create -n gpy --yes
conda install -c conda-forge pytorch xarray=0.16 pytorch torchvision cudatoolkit --yes
conda install -c conda-forge netcdf4 numba tqdm jupyterlab tensorboard ipython pip ruamel.yaml descartes statsmodels scikit-learn black mypy --yes
pip install gpytorch

tommylees112

from typing import Dict 
import xarray as xr 
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from pathlib import Path

def scatter_plot(obs: np.ndarray, sim: np.ndarray, ax = None, scatter_kwargs: Dict = {"marker": "x", "color": "C0", "alpha": 0.3}):
    if ax is None:
        f, ax = plt.subplots(figsize=(6, 6))

tommylees112

from typing import Tuple, Any, Union, List
import pandas as pd
import datetime as dt 
from pathlib import Path 
import numpy as np


def find_nearest(array: Union[np.ndarray, List[float]], value: float) -> Tuple[Any, int]:
    # https://stackoverflow.com/a/2566508/9940782
    array = np.asarray(array)

tommylees112

# conda install -c conda-forge xarray --yes
import xarray as xr 
import pandas as pd
from pathlib import Path
import matplotlib.pyplot as plt

data_dir = Path("path/to/data")

# open the data
dynamic = xr.open_dataset(data_dir / "ALL_dynamic_ds.nc")

tommylees112

import napari
import xarray as xr 
from pathlib import Path

data_dir = Path("/path/to/data")

# open data
ds = xr.open_dataset(data_dir / "data.nc")
da = ds["VARIABLE_NAME"]

tommylees112

conda create -n napari python=3.8 --yes
conda activate napari
conda install -c conda-forge napari xarray netcdf4 ipython pip
pip install 'napari[all]'

tommylees112

frmo typing import Dict, Union
import xarray as xr 
import pandas as pd
from pathlib import Path


def save_scaler(scaler: Dict[str, Union[xr.Dataset, pd.DataFrame]], run_dir: Path) -> None:
    """Save scaler to disk as separate netcdf files"""
    scaler_dir = run_dir / "train_data"
    for k, v in scaler.items():