On Sun, Oct 6, 2019 at 4:24 PM Eric Berger <ericjber...@gmail.com> wrote:
> [Sending your follow-on question to the full R-help list]
>
> On Fri, Oct 4, 2019 at 7:13 PM javed khan <javedbtk...@gmail.com> wrote:
>
> > Thanks for your reply. I checked the example of treatment and control but
> > I can not understand the first four lines. How can we do it if we have
> the
> > data (both columns) in excel and we read it in code with read.csv.
> >
> > Best regards
> >
> > On Friday, October 4, 2019, Eric Berger <ericjber...@gmail.com> wrote:
> >
> >> For general documentation about the effsize package you would do:
> >> > help(package="effsize")
> >>
> >> For information on calculations related to vargha:
> >> >??vargha
> >> This command displays effsize::VD.A, which you can find out about via
> the
> >> command
> >> >?effsize::VD.A
> >> This displays the documentation for the function VD.A. At the top of the
> >> documentation you have the Description and Usage sections. At the bottom
> >> there are some examples of using the function.
> >>
> >> HTH,
> >> Eric
> >>
> >>
> >> On Fri, Oct 4, 2019 at 10:44 AM javed khan <javedbtk...@gmail.com>
> wrote:
> >>
> >>> I am new to R language. I have two column data I.e X= 0.23, 0.04, 0.5,
> -
> >>> 0.20 etc and B= 0.34, 0.01, 0.1, 0.09 etc. The number of observations
> are
> >>> 100. How can I apply vargha and delaney effect size in R? I load the
> data
> >>> as, read.csv(mydata.csv) and load the library effsize. Please if
> someone
> >>> can help because I have no idea about the next step to follow.
> >>>
> >>> Thanks
> >>>
> >>> [[alternative HTML version deleted]]
> >>>
> >>> ______________________________________________
> >>> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> >>> https://stat.ethz.ch/mailman/listinfo/r-help
> >>> PLEASE do read the posting guide
> >>> http://www.R-project.org/posting-guide.html
> >>> and provide commented, minimal, self-contained, reproducible code.
> >>>
> >>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
# -*- coding: utf-8 -*-
"""
Created on Sun Oct 6 13:19:06 2019
@author: khh
"""
###############################################################################
print('#################### plottong ##################################')
###############################################################################
import matplotlib.pyplot as plt
# plt.rcParams["font.family"] = "Times New Roman"
params = {
'font.family': 'Times New Roman',
'axes.labelsize': 8,
'text.fontsize': 8,
'legend.fontsize': 10,
'xtick.labelsize': 7, #8
'ytick.labelsize': 9,
'text.usetex': False,
'figure.figsize': [7, 4] # instead of 4.5, 4.5
}
plt.rcParams.update(params)
### descriptive statistics
#
X.describe()
### num_dpi = 300, 600
def export_plot (plot_name, num_dpi):
plt.savefig('Fig_' + plot_name + '_plot1.png', dpi = num_dpi,
bbox_inches='tight', pad_inches = 0.01)
plt.savefig('Fig_' + plot_name + '_plot1.tiff', dpi = num_dpi,
bbox_inches='tight', pad_inches = 0.01, format="tiff",
pil_kwargs={"compression": "tiff_lzw"})
# =============================================================================
# ### save plots
# plt.savefig('SHOPA_' + area_type2 + '_plot1.png', dpi=600,
bbox_inches='tight', pad_inches = 0.01)
# plt.savefig('SHOPA_' + area_type2 + '_plot1.tiff', dpi=600,
bbox_inches='tight', pad_inches = 0.01, format="tiff",
pil_kwargs={"compression": "tiff_lzw"})
#
# =============================================================================
### plot histo
plt.figure();
X.plot.hist(alpha = 0.5)
plt.show()
export_plot('testplot' , 600)
plt.show()
# X.diff().hist(color='k', alpha=0.5, bins=50)
# plt.show()
# =============================================================================
# # Plot the raw time series
# fig = plt.figure(constrained_layout=True)
# gs = gridspec.GridSpec(2, 3, figure=fig)
# ax = fig.add_subplot(gs[0, :])
# ax.plot(t, y)
# ax.set_xlabel('time [s]')
# ax.set_ylabel('signal')
#
# =============================================================================
### Good
plt.figure()
# fig, (ax0, ax1) = plt.subplots(ncols=2, constrained_layout=True)
fig, ax1 = plt.subplots(ncols=1, constrained_layout=True)
X.plot.box()
fig = X.plot(subplots=True, figsize=(6, 6));
fig.X.subplot()
### Stacking subplots in two directions
### When stacking in two directions, the returned axs is a 2D numpy array.
#
# If you have to set parameters for each subplot it's handy to iterate over all
subplots in a 2D grid using for ax in axs.flat:.
#
### 'q_hosheal2_MEAN', 'q_khos2_MEAN', 'q_dhos3_MEAN'
fig, axs = plt.subplots(2, 2)
axs[0, 0].plot(X['q_hos1_MEAN'], bins = 10)
axs[0, 0].set_title('Axis [0,0]')
axs[0, 1].plot(X['q_hosheal2_MEAN'], bins = 10) #, 'tab:orange')
axs[0, 1].set_title('Axis [0,1]')
axs[1, 0].plot(X['q_khos2_MEAN'], bins =10 )#, 'tab:green')
axs[1, 0].set_title('Axis [1,0]')
axs[1, 1].plot(X['q_dhos3_MEAN'], bins = 10)#, 'tab:red')
axs[1, 1].set_title('Axis [1,1]')
for ax in axs.flat:
ax.set(xlabel='x-label', ylabel='y-label')
# Hide x labels and tick labels for top plots and y ticks for right plots.
for ax in axs.flat:
ax.label_outer()
### bin must
import matplotlib.pyplot as plt
plt.subplot(2, 1, 1)
plt.plot(X['q_hos1_MEAN'], y, '-', linewidth = 0.1) # 'o-')
plt.title('A tale of 2 subplots')
plt.ylabel('Damped oscillation')
plt.subplot(2, 1, 2)
plt.plot(X['q_hosheal2_MEAN'], y, '.-', linewidth = 0.2)
plt.xlabel('time (s)')
plt.ylabel('Undamped')
plt.show()
export_plot('testplot' , 600)
### Good fig
plt.figure();
X.plot.hist(stacked=True, bins=20)
### hist bin must
import matplotlib.pyplot as plt
plt.figure(figsize = [6.4, 4.8], dpi = 600); # [6.4, 4.8/9.0], dpi = 600);
plt.subplot(4, 1, 1)
plt.hist(X['q_hos1_MEAN'], bins= 10) #, linewidth = 0.1)
plt.title('Histogram plot: hos1')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.subplot(4, 1, 2)
plt.hist(X['q_hosheal2_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: hosheal2')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.subplot(4, 1, 3)
plt.hist(X['q_khos2_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: khos2')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.subplot(4, 1, 4)
plt.hist(X['q_dhos3_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: dhos3')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
# plt.tight_layout()
export_plot('Xvars_histogram_plot4' , 600)
plt.show()
#### Good:
plt.figure(figsize = [6.4, 4.8], dpi = 600); # [6.4, 4.8/9.0], dpi = 600);
plt.subplot(1, 1, 1)
plt.hist(X['q_hos1_MEAN'], bins= 10) #, linewidth = 0.1)
plt.title('Histogram plot: hos1')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Xvars_histogram_plot4=q_hos1' , 600)
plt.show()
plt.subplot(1, 1, 1)
plt.hist(X['q_hosheal2_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: hosheal2')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Xvars_histogram_plot4=q_hosheal2' , 600)
plt.show()
plt.subplot(1, 1, 1)
plt.hist(X['q_khos2_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: khos2')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Xvars_histogram_plot4=q_khos2' , 600)
plt.show()
plt.subplot(1, 1, 1)
plt.hist(X['q_dhos3_MEAN'], bins = 10) #, linewidth = 0.2)
plt.title('Histogram plot: dhos3')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Xvars_histogram_plot4=q_dhos3' , 600)
plt.show()
plt.figure(figsize = [6.4, 4.8], dpi = 600); # [6.4, 4.8/9.0], dpi = 600);
plt.subplot(1, 1, 1)
plt.hist(y, bins= 10) #, linewidth = 0.1)
plt.title('Histogram plot: y(B7_2)')
plt.xlabel('Facility satisfaction')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Yvars_histogram_plot4=y(B7_2)' , 600)
plt.show()
###
plt.figure(figsize = [6.4, 4.8], dpi = 600); # [6.4, 4.8/9.0], dpi = 600);
# df.columns.tolist()
factor1 = df[['q_hos3_MEAN',
'q2_clc2_MEAN','q_hos2_MEAN','q2_clc3_MEAN','q2_clc32_MEAN','q_dhos2_MEAN','q_hos0_MEAN',
'q_drug3_MEAN']]
corr = factor1.corr()
import seaborn as sns
ax = sns.heatmap(
corr,
vmin=-1, vmax=1, center=0,
cmap=sns.diverging_palette(20, 220, n=200),
square=True
)
ax.set_xticklabels(
ax.get_xticklabels(),
rotation=45,
horizontalalignment='right'
);
export_plot('geoqol2016_corrplot1=factor1' , 600)
plt.show()
### corrplot for factors_all
factors_all = df[['q_hos3_MEAN','q_hosheal2_MEAN','q2_clc2_MEAN','q_hos2_MEAN',
'q2_clc3_MEAN','q2_clc32_MEAN','q_dhos2_MEAN','q_hos0_MEAN',
'q_khos2_MEAN','q_dhos3_MEAN','q_birth_MEAN','q2_clc1_MEAN',
'q_hos1_MEAN','q_drug3_MEAN']]
corr = factors_all.corr()
import seaborn as sns
ax = sns.heatmap(
corr,
vmin=-1, vmax=1, center=0,
cmap=sns.diverging_palette(220, 20, sep=20, as_cmap=True), #(20, 220,
n=200), # 220, 20, sep=20, as_cmap=True)
square=True
)
ax.set_xticklabels(
ax.get_xticklabels(),
rotation=45,
horizontalalignment='right'
);
export_plot('geoqol2016_corrplot1=factors_all' , 600)
plt.show()
###
plt.hist(corr)
labels= list(factors_all)
plt.legend(labels)
# plt.legend(prop={'size': 8})
# plt.plot(corr. corr)
export_plot('geoqol2016_corrplot_2=factors_all' , 600)
plt.show()
###
plt.subplot(1, 1, 1)
plt.plot(factor1, linewidth = 0.1)
plt.title('Histogram plot: hos1')
plt.xlabel('Distance(meters)')
plt.ylabel('Freq.')
plt.tight_layout()
export_plot('Xvars_histogram_plot4=q_dhos3' , 600)
plt.show()
### Good fig
plt.figure();
X.plot.hist(stacked=True, bins=20)
plt.figure();
plt.hist(X['q_hos1_MEAN'], bins= 10, linewidth = 0.1) # 'o-')
plt.show()
### Hexagonal bin plot
#
# X.plot.hexbin(x= 'q_hos1_MEAN', y= y, gridsize=25)
###
from pandas.plotting import andrews_curves
plt.figure()
# andrews_curves(X, 'q_hos1_MEAN') # (data, 'Name')
plt.show()
# shap.summary_plot(shap_values, final_model_features)
# plt.savefig('shap.force_plot1.png')
###
from pandas.plotting import radviz
#
radviz(X, 'q_hos1_MEAN')
plt.show()
### subplots
#
X.columns.tolist()
# df[['q_hos1_MEAN', 'q_hosheal2_MEAN', 'q_khos2_MEAN',
'q_dhos3_MEAN']].plot(subplots=True, figsize=(6, 6), linewidth=0.5,
linestyle='-', color='#006BB2')
X.plot(subplots=True, figsize=(6, 6), linewidth=0.5, linestyle='-',
color='#006BB2') # linewidth=2, linestyle='--', color='#006BB2')
# plt.show()
export_plot('???', 600)
plt.show()
#
plt.figure()
X.plot(subplots=True, layout=(2, 2), figsize=(6, 6), linewidth=0.5,
sharex=False);
# plt.show()
export_plot('???', 600)
plt.show()
### imporing DPI in folders
from PIL import Image
import glob
import os
DPI = 600
cwd = os.getcwd()
cwd =
'C://0.DATA/_pywork/data_ML/geoqol2016/ML_qol_models/geoqol2016_2019-10-03_VIFunchecked_FAn=4confirmed/dpi600'
os.chdir(cwd)
list_img = glob.glob('*') #('*.png') ###("*")
for img in list_img:
im = Image.open(img)
im.save(img, dpi=(DPI,DPI))
print(img)
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
