marcosfelt

marcosfelt

from typing import Dict, List, Literal
from scipy.stats import linregress, spearmanr
from sklearn import metrics

SCORE_NAMES = ["mae", "mse", "rmse", "mape", "r2", "maxe", "expl_var"]
def calculate_metrics(

    y_true, y_pred, scores: List[str] = SCORE_NAMES
) -> Dict[str, float]:
    """Calculate metrics on a given dataset."""

marcosfelt

import logging
import re
from typing import Tuple, Union

import pandas as pd
import requests
from bs4 import BeautifulSoup
from tqdm import tqdm

wikipedia_base = "https://en.wikipedia.org"

marcosfelt

import numpy as np

def pareto_efficient(data, maximize=True):
    """
    Copied from Summit, which in turn was probably copied from Stackoverflow
    Find the pareto-efficient points
    Parameters
    ---------
    data: array-like
        An (n_points, n_data) array

marcosfelt

from typing import Dict, List, Optional
import matplotlib as mpl
from matplotlib.axes import Axes
import matplotlib.pyplot as plt
import numpy as np

def parity_plot(
    y,
    yhat,
    ax: Optional[Axes] = None,

marcosfelt

import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import cm, ticker
from matplotlib.axes import Axes
from matplotlib.figure import Figure
from scipy.interpolate import make_interp_spline
from typing import Callable, Dict, List, Optional, Union

marcosfelt

from rdkit import Chem

"""The code below is directly copied from the thermo group_contribution code (MIT license) 
https://github.com/CalebBell/thermo/blob/516dee4ceda8e100918c7645e393a42fdfdc4bef/thermo/group_contribution/

I made changes to the SMARTS strings to match the ones used in FeOs
"""
J_BIGGS_JOBACK_SMARTS = [
    ["Methyl", "CH3", "[CX4H3]"],
    ["Secondary acyclic", "CH2", "[!R;CX4H2]"],

marcosfelt

import numpy as np
x = np.arange(100)
N = 0
mean = 0
std = 0
for i in range(11):
    batch = x[10*i:10*(i+1)]
    k = len(batch)
    N += k
    old_mean = mean

marcosfelt

// Copyright (C) 2003 Rational Discovery LLC
//  This file is part of the RDKit.
//  The contents are covered by the terms of the BSD license
//  which is included in the file license.txt, found at the root
//  of the RDKit source tree.
// NOTES:
//  - larger functional groups should come before smaller ones involving
//    the same core atom
//  - the first atom in the SMARTS query is not part of the group itself
//  - it is essential that the fields in this file be separated by tabs

marcosfelt

import pandas as pd
import numpy as np
from lmfit import minimize, Parameters

import ray
from ray.exceptions import GetTimeoutError

from tqdm.auto import tqdm, trange
import typer