larsbratholm

4

H          1.01361       -0.43872        0.05166
H         -0.37629       -0.59645        0.04850
H          1.62350       -1.33635        0.06931
H         -0.80859       -1.59316        0.06357

larsbratholm

3

H         -0.65849        1.79875        0.00662
H          0.73147        1.95418        0.00966
H         -1.29266        2.67914       -0.01097

larsbratholm

2

H          2.96821        1.08475        0.03403
H          3.24493        2.05794        0.01754

larsbratholm

20
	Energy:     -11.4541449
C         -1.20080        0.52014        0.02618
C         -0.65849        1.79875        0.00662
C          0.73147        1.95418        0.00966
C          1.58002        0.83735        0.03236
C          1.01361       -0.43872        0.05166
C         -0.37629       -0.59645        0.04850
C          3.99063        0.15254        0.05602
C          5.34795        0.81013        0.04860

larsbratholm

"""
Calculate 95% confidence interval for rapported MAE. 
The data is assumed to follow a laplacian distribution.
See https://waset.org/publications/8809/confidence-intervals-for-double-exponential-distribution-a-simulation-approach
for derivation.
"""

import numpy as np
import scipy.stats as ss

larsbratholm

def jread(filename, atomnumber):

    couplings = np.zeros((atomnumber, atomnumber), dtype=float)
    with open(filename) as f:
        skip = True
        for line in f:
            if "Total nuclear spin-spin coupling J (Hz):" in line:
                skip = False
                continue
            elif "End of Minotr" in line:

larsbratholm

import numpy as np
from sklearn.linear_model import Lasso, LinearRegression

# Generate 100 samples of y = x**2 plus some small random error
n = 100
x = np.random.random(100)
y = x**2 + 0.1*np.random.random(n)
# Create [x,x**2] as different features
f = np.asarray([x,x**2]).T
# Train a linear regression model as comparison

larsbratholm

outer_cv = KFold(5, shuffle=True)

for train, test in outer_cv.split(range(n_datapoints)):
    for n in [100, 300, 1000, 3000, 10000, 30000, 100000]:
        # save file for osprey containing the indices of train[:n]
        # save file with test indices to get test errors after finding best params with osprey

larsbratholm

import numpy as np
import copy

K # shape (N,N)

# Create a list with all the indices of the submatrix
idx = np.arange(N-1) + 1
for i in range(N):
    # when i==0, idx will be [1,2,3,4...]
    # when i==1, idx will become [0,2,3,4...] etc

larsbratholm

from simtk import openmm, unit
from simtk.openmm import app
import numpy as np
import sys

# Create an integrator
timestep = 1.0 * unit.femtoseconds
integrator = openmm.VerletIntegrator(timestep)

# Open Amber files