CHEERSafe Tools, Sampling, and Covariance¶

This notebook demonstrates utility JSON loading, deterministic seed derivation, Latin Hypercube sampling, and covariance matrix construction.

In [1]:

from pathlib import Path
import os

repo_root = Path.cwd()
while not (repo_root / "pyproject.toml").exists() and repo_root != repo_root.parent:
    repo_root = repo_root.parent
os.chdir(repo_root)
repo_root

from pathlib import Path import os repo_root = Path.cwd() while not (repo_root / "pyproject.toml").exists() and repo_root != repo_root.parent: repo_root = repo_root.parent os.chdir(repo_root) repo_root

Out[1]:

PosixPath('/home/mammad/Documents/EDU/cope/CHEERSafe/LossModel')

In [2]:

from cheersafe.config import Config

Config.reset_flags()
Config.NUM_OF_WORKERS = 1
Config.NUM_OF_WORKERS_SAMPLING = 1
Config.RANDOM_SEED = 42

from cheersafe.config import Config Config.reset_flags() Config.NUM_OF_WORKERS = 1 Config.NUM_OF_WORKERS_SAMPLING = 1 Config.RANDOM_SEED = 42

In [3]:

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

from cheersafe.tools import Covariance, Sampling, Utils

import matplotlib.pyplot as plt import numpy as np import pandas as pd from cheersafe.tools import Covariance, Sampling, Utils

In [4]:

wind = Utils.from_json("Inputs/WindSpeed.json")
pd.DataFrame(wind[:5], columns=["ID", "mph", "m/s"])

wind = Utils.from_json("Inputs/WindSpeed.json") pd.DataFrame(wind[:5], columns=["ID", "mph", "m/s"])

Out[4]:

	ID	mph	m/s
0	1.0	0.0	0.0
1	2.0	50.0	22.4
2	3.0	55.0	24.6
3	4.0	60.0	26.8
4	5.0	65.0	29.1

In [5]:

mean = np.array([50.0, 70.0, 100.0])
cv = np.array([0.3, 0.3, 0.25])
num_component = [1, 1, 1]
sigma = Covariance.create_cov_matrix(num_component, mean, cv)
samples = Sampling.generate_lhs_samples_norm(25, mean, sigma, seed=Sampling.derive_seed("docs", 1))
pd.DataFrame(samples, columns=["RC", "RS", "RWC"]).head()

mean = np.array([50.0, 70.0, 100.0]) cv = np.array([0.3, 0.3, 0.25]) num_component = [1, 1, 1] sigma = Covariance.create_cov_matrix(num_component, mean, cv) samples = Sampling.generate_lhs_samples_norm(25, mean, sigma, seed=Sampling.derive_seed("docs", 1)) pd.DataFrame(samples, columns=["RC", "RS", "RWC"]).head()

Out[5]:

	RC	RS	RWC
0	45.900267	86.662773	93.131695
1	47.933084	93.625396	85.647669
2	35.563607	90.099257	106.525827
3	57.853936	81.760623	123.493018
4	67.864456	90.823721	113.562629

In [6]:

fig, ax = plt.subplots(figsize=(6, 4))
ax.scatter(samples[:, 0], samples[:, 1], alpha=0.8)
ax.set_xlabel("Roof covering sample")
ax.set_ylabel("Roof sheathing sample")
ax.set_title("Deterministic LHS samples")
ax.grid(True, alpha=0.3)
plt.show()

fig, ax = plt.subplots(figsize=(6, 4)) ax.scatter(samples[:, 0], samples[:, 1], alpha=0.8) ax.set_xlabel("Roof covering sample") ax.set_ylabel("Roof sheathing sample") ax.set_title("Deterministic LHS samples") ax.grid(True, alpha=0.3) plt.show()

In [7]:

Config.reset_flags()
print(Sampling.resolve_seed())

Config.reset_flags() print(Sampling.resolve_seed())

42