def plotit(what):
if what == "DHI":
plotme = np.stack((Y_C, DHI), axis=1)
else:
plotme = np.stack((Y_C, D13C), axis=1)
plotmeX, plotmeY = dropna(plotme, country_codes)
plotmeX, plotmeY = drop_lowNs(plotmeX, plotmeY, threshold=5)
category_frequencies(plotmeY)
plot(plotmeX, plotmeY, axlabels=["Y", what])
def split_by_CCode(param):
bycat = split_by_categories(CCode)
new = {}
for cat in bycat:
catargs = bycat[cat]
fX, fCoord = dropna(param[catargs], Y_C[catargs])
if not np.prod(fX.shape):
continue
new[cat] = [fX.mean(), fX.std(), fCoord.mean()]
return new
def assemble_X(pnm):
param = globals()[pnm]
fP, fX, fY, flabel = dropna(param, X_C, Y_C, CCode)
split = split_by_categories(flabel, np.stack((fP, fX, fY), axis=1))
data = ["\t".join(("GEO", pnm, "X", "Y"))]
for label, array in split.items():
if len(array) > 0:
mean = array.mean(axis=0)
else:
mean = array.mean(axis=0)
data.append("\t".join([label] + mean.astype(str).tolist()))
with open(projectroot + pnm + "_MEANS.csv", "w") as handle:
handle.write("\n".join(data).replace(".", ","))
print(pnm, "assembled!")
import numpy as np
from csxdata.stats.inspection import category_frequencies
from csxdata.utilities.highlevel import plot
from csxdata.utilities.parser import parse_csv
from csxdata.utilities.vectorop import drop_lowNs, dropna
from SciProjects.sophie import projectroot
X, Y, head = parse_csv(projectroot + "01GEO.csv",
indeps=4, headers=1, decimal=True)
y_coord = Y[:, -1].astype(float)
categ = Y[:, 0]
DHI, D13C = X.T
plotme = np.stack((DHI, D13C, y_coord), axis=1)
plotme, categ = dropna(plotme, categ)
category_frequencies(categ)
plot(plotme, axlabels=["DHI", "D13C", "Y"])
def correlate(pnm):
param = globals()[pnm]
X, Y = dropna(param, Y_C)
return stats.spearmanr(X, Y)
from SciProjects.sophie import projectroot
from csxdata.utilities.parser import parse_csv
from csxdata.utilities.vectorop import dropna
from csxdata.stats.inspection import category_frequencies, correlation
from csxdata.stats.normaltest import full
X, Y, head = parse_csv(projectroot + "01GEO.csv",
indeps=2,
headers=1,
decimal=True)
category_frequencies(Y)
X, Y = dropna(X, Y)
correlation(X, ["X", "Y", "DH1", "DH2"])
full(X)
def plotit3d():
plotme = np.stack((Y_C, DHI, D13C), axis=1)
plotmeX, plotmeY = dropna(plotme, country_codes)
category_frequencies(plotmeY)
plot(plotmeX, plotmeY, axlabels=["Y", "DHI", "D13C"])
from matplotlib import pyplot as plt
from csxdata.utilities.parser import parse_csv
from csxdata.utilities.vectorop import dropna
from csxdata.utilities.highlevel import plot
from SciProjects.sophie import projectroot
X, Y, head = parse_csv(projectroot + "01GEO.csv",
indeps=4,
headers=1,
decimal=True)
y_coord = Y[:, -1].astype(float)
countries = Y[:, 0]
DHI, D13C = X.T
plot(np.stack((y_coord, DHI), axis=1), countries, axlabels=["Y", "DHI"])
plotme, c2 = dropna(np.stack((y_coord, D13C), axis=1), countries)
plot(plotme, c2, ["Y", "D13C"])
fig, axarr = plt.subplots(2)
axarr[0].scatter(y_coord, DHI, color="red", marker=".")
axarr[0].set_xlabel(r"$(D/H)_I$")
axarr[1].scatter(y_coord, D13C, color="red", marker=".")
axarr[1].set_xlabel(r"$\delta^13C$")
axarr[0].set_ylabel("Y")
axarr[1].set_ylabel("Y")
plt.tight_layout()
plt.show()
import numpy as np
from scipy import stats
from matplotlib import pyplot as plt
from csxdata.visual import Plotter2D
from csxdata.utilities.vectorop import dropna
from csxdata.stats.inspection import category_frequencies
from SciProjects.sophie import pull_data, axtitles
X_C, Y_C, DHI, D13C, CCode = pull_data("04GEO_eu.csv")
DHI, Y_C, CCode = dropna(DHI, Y_C, CCode)
category_frequencies(CCode)
R, p = stats.spearmanr(DHI, Y_C)
line = np.polyfit(Y_C, DHI, 1)
line = np.poly1d(line)
ttl = (
"Korreláció $(D/H)_I$ és az egyenlítőtől való távolság között Európában",
f"Spearman-korreláció: R = {R:.2f}, p = {p:.2f}, {('nem' if p > 0.05 else '')}szignifikáns"
)
axttl = ["Egyenlítőtől való távolság", axtitles["DHI"]]
plotter = Plotter2D(plt.figure(),
np.stack((Y_C, DHI), axis=1),
CCode,
title="\n".join(ttl),
axlabels=axttl)
plotter.split_scatter(center=True, sigma=2, alpha=0.5)