tikz/histogram-symbols: Added

tikz/histogram-symbols/1ddata.txt

@@ -0,0 +1,369 @@
+3514
+3400
+2914
+2601
+2567
+2518
+2413
+2378
+2296
+2179
+2139
+2041
+2008
+1910
+1759
+1576
+1533
+1528
+1527
+1522
+1509
+1452
+1402
+1399
+1385
+1337
+1306
+1286
+1246
+1235
+1217
+1186
+1147
+1140
+1136
+1131
+1123
+1112
+1101
+1098
+1076
+1068
+1067
+1066
+1054
+1016
+1008
+996
+996
+980
+978
+950
+948
+929
+923
+916
+915
+910
+903
+887
+880
+875
+872
+867
+866
+861
+843
+823
+804
+799
+773
+773
+772
+763
+762
+762
+758
+755
+743
+741
+733
+692
+687
+686
+671
+667
+651
+641
+631
+624
+621
+607
+569
+562
+557
+549
+544
+532
+523
+519
+514
+511
+505
+489
+486
+474
+461
+461
+453
+448
+441
+424
+420
+417
+415
+411
+408
+404
+402
+399
+398
+398
+393
+391
+387
+383
+380
+370
+362
+362
+359
+359
+356
+350
+348
+347
+345
+336
+336
+335
+330
+330
+329
+321
+320
+316
+314
+312
+311
+304
+298
+296
+288
+286
+282
+282
+279
+277
+275
+274
+270
+268
+267
+264
+261
+260
+259
+252
+251
+250
+243
+242
+241
+240
+240
+240
+240
+239
+238
+237
+237
+231
+227
+227
+223
+222
+222
+221
+221
+219
+217
+215
+214
+213
+209
+209
+209
+204
+204
+203
+202
+201
+201
+199
+198
+195
+194
+193
+193
+185
+185
+184
+184
+184
+184
+183
+183
+181
+180
+176
+175
+175
+171
+167
+167
+167
+164
+163
+163
+160
+160
+159
+159
+156
+156
+155
+154
+152
+150
+150
+150
+149
+148
+147
+147
+146
+144
+143
+142
+142
+141
+141
+140
+139
+139
+139
+139
+138
+135
+134
+133
+133
+132
+132
+127
+127
+126
+124
+124
+123
+121
+121
+121
+121
+120
+120
+119
+118
+118
+118
+118
+115
+115
+115
+114
+114
+114
+113
+112
+111
+111
+111
+110
+108
+107
+105
+105
+105
+104
+103
+101
+101
+101
+101
+100
+100
+99
+99
+98
+97
+97
+96
+95
+94
+90
+90
+90
+86
+84
+83
+78
+75
+72
+72
+69
+67
+67
+66
+66
+66
+65
+64
+63
+63
+63
+62
+62
+61
+61
+61
+61
+60
+60
+59
+59
+59
+58
+58
+58
+58
+58
+57
+57
+57
+56
+56
+56
+56
+56
+56
+56
+56
+56
+55
+54
+54
+53
+53
+51

tikz/histogram-symbols/Makefile

@@ -0,0 +1,35 @@
+SOURCE = histogram-large-1d-dataset
+DELAY = 80
+DENSITY = 300
+WIDTH = 512
+
+make:
+	pdflatex $(SOURCE).tex -output-format=pdf
+	make clean
+
+clean:
+	rm -rf  $(TARGET) *.class *.html *.log *.aux *.data *.gnuplot
+
+gif:
+	pdfcrop $(SOURCE).pdf
+	convert -verbose -delay $(DELAY) -loop 0 -density $(DENSITY) $(SOURCE)-crop.pdf $(SOURCE).gif
+	make clean
+
+png:
+	make
+	make svg
+	inkscape $(SOURCE).svg -w $(WIDTH) --export-png=$(SOURCE).png
+
+transparentGif:
+	convert $(SOURCE).pdf -transparent white result.gif
+	make clean
+
+svg:
+	make
+	#inkscape $(SOURCE).pdf --export-plain-svg=$(SOURCE).svg
+	pdf2svg $(SOURCE).pdf $(SOURCE).svg
+	# Necessary, as pdf2svg does not always create valid svgs:
+	inkscape $(SOURCE).svg --export-plain-svg=$(SOURCE).svg
+	rsvg-convert -a -w $(WIDTH) -f svg $(SOURCE).svg -o $(SOURCE)2.svg
+	inkscape $(SOURCE)2.svg --export-plain-svg=$(SOURCE).svg
+	rm $(SOURCE)2.svg

tikz/histogram-symbols/README.md

@@ -0,0 +1,12 @@
+Compiled example
+----------------
+![Example](histogram-large-1d-dataset.png)
+
+Credits
+--------
+
+Thanks to [esdd](http://tex.stackexchange.com/users/43317/esdd) who helped me
+to get the LaTeX part work (see [tex.SE answer](http://tex.stackexchange.com/a/194966/5645))
+
+Thanks to [jenson_bo](http://tex.stackexchange.com/users/17775/jenson-bo) for
+making it beautiful!

tikz/histogram-symbols/histogram-large-1d-dataset.template.tex

@@ -0,0 +1,55 @@
+\documentclass[margin=10pt]{standalone}
+\usepackage{amsmath}
+\usepackage{pgfplots}
+\pgfplotsset{compat=1.3}
+
+\newcommand\clipright[1][white]{
+  \fill[#1](current axis.south east)rectangle(current axis.north-|current axis.outer east);
+  \pgfresetboundingbox
+  \useasboundingbox(current axis.outer south west)rectangle([xshift=.5ex]current axis.outer north-|current axis.east);
+}
+
+\definecolor{mycolor}{rgb}{0.02,0.4,0.7}
+
+\begin{document}
+\begin{tikzpicture}
+    \begin{axis}[
+        ymajorgrids,
+        xmajorgrids,
+        grid style={white,thick},
+        axis on top,
+        /tikz/ybar interval,
+        tick align=outside,
+        ymin=0,
+        axis line style={draw opacity=0},
+        tick style={draw=none},
+        enlarge x limits=false,
+        height=5cm,
+        title style={font=\Large},
+        xlabel={Collected Labeled Recordings},
+        ylabel={Number of Symbols},
+        ytick={ {{yticks}} },
+        scaled ticks=false,
+        yticklabels={ {{yticklabels}} },
+        xticklabels={ {{xticklabels}} },
+        width=\textwidth,
+        xtick=data,
+        label style={font=\large},
+        ticklabel style={
+            inner sep=1pt,
+            font=\small
+        },
+        nodes near coords,
+        every node near coord/.append style={
+            fill=white,
+            anchor=mid west,    
+            shift={(3pt,4pt)},
+            inner sep=0,
+            font=\footnotesize,
+            rotate=45},
+            ]
+    \addplot[mycolor!80!white, fill=mycolor, draw=none] coordinates { {{coordinates}} };
+    \end{axis}
+    \clipright
+\end{tikzpicture}
+\end{document}

tikz/histogram-symbols/histogram-large-1d-dataset.tex

@@ -0,0 +1,55 @@
+\documentclass[margin=10pt]{standalone}
+\usepackage{amsmath}
+\usepackage{pgfplots}
+\pgfplotsset{compat=1.3}
+
+\newcommand\clipright[1][white]{
+  \fill[#1](current axis.south east)rectangle(current axis.north-|current axis.outer east);
+  \pgfresetboundingbox
+  \useasboundingbox(current axis.outer south west)rectangle([xshift=.5ex]current axis.outer north-|current axis.east);
+}
+
+\definecolor{mycolor}{rgb}{0.02,0.4,0.7}
+
+\begin{document}
+\begin{tikzpicture}
+    \begin{axis}[
+        ymajorgrids,
+        xmajorgrids,
+        grid style={white,thick},
+        axis on top,
+        /tikz/ybar interval,
+        tick align=outside,
+        ymin=0,
+        axis line style={draw opacity=0},
+        tick style={draw=none},
+        enlarge x limits=false,
+        height=5cm,
+        title style={font=\Large},
+        xlabel={Collected Labeled Recordings},
+        ylabel={Number of Symbols},
+        ytick={ 0,20,40,60,80,100 },
+        scaled ticks=false,
+        yticklabels={ 0, 20, 40, 60, 80, 100 },
+        xticklabels={ $0$, $100$, $200$, $300$, $400$, $500$, $600$, $\infty$ },
+        width=\textwidth,
+        xtick=data,
+        label style={font=\large},
+        ticklabel style={
+            inner sep=1pt,
+            font=\small
+        },
+        nodes near coords,
+        every node near coord/.append style={
+            fill=white,
+            anchor=mid west,    
+            shift={(3pt,4pt)},
+            inner sep=0,
+            font=\footnotesize,
+            rotate=45},
+            ]
+    \addplot[mycolor!80!white, fill=mycolor, draw=none] coordinates { (0, 122) (1, 66) (2, 39) (3, 30) (4, 12) (5, 9) (6, 10) (7, 70)  };
+    \end{axis}
+    \clipright
+\end{tikzpicture}
+\end{document}

tikz/histogram-symbols/process.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from __future__ import print_function
+import shutil
+import fileinput
+import math
+
+
+def main(filename, bins, maximum, yticks_number):
+    with open(filename) as f:
+        content = f.read().split("\n")
+    numbers = []
+    for line in content:
+        line = line.strip()
+        if line != "":
+            numbers.append(float(line))
+    numbers = sorted(numbers)
+    minimum = min(numbers)
+    bin_counter = [0 for i in range(bins+1)]
+    xticklabels = []
+    for i, number in enumerate(numbers):
+        if number >= minimum + (maximum - minimum)/bins*(bins+1):
+            bin_counter[bins] += 1
+        elif number < minimum:
+            bin_counter[0] += 1
+        else:
+            for b in range(bins):
+                lower = minimum + (maximum - minimum)/bins*b
+                upper = minimum + (maximum - minimum)/bins*(b+1)
+                if lower <= number < upper:
+                    bin_counter[b] += 1
+                    break
+    minimum = 0
+    for b in range(bins):
+        lower = minimum + (maximum - minimum)/bins*b
+        xticklabels.append(get_xticklabel(lower))
+
+    # Get labels for y-axis
+    yticks = []
+    ytickslabels = []
+    maxy = max(bin_counter)
+    maxylabel = int(10**math.floor(math.log(maxy, 10)))*int(str(maxy)[0])
+    ylabelsteps = int(math.ceil(maxylabel / yticks_number))
+    if ylabelsteps == 0:
+        ylabelsteps = 1
+    for i in range(0, maxylabel+1, ylabelsteps):
+        print("i: %i, %i" % (i, maxylabel))
+        print("label: %i%s" % get_si_suffix(i))
+        yticks.append(str(i))
+        ytickslabels.append(get_yticklabel(i, True))
+
+    xticklabels.append("\infty")
+    return bin_counter, xticklabels, ytickslabels, yticks
+
+
+def get_xticklabel(value):
+    return str(int(value))
+
+
+def get_yticklabel(value, si_suffix):
+    value = float(value)
+    if si_suffix:
+        divide_by, suffix = get_si_suffix(value)
+        new_value = (value / divide_by)
+        if int(new_value) == new_value:
+            return ("%i" % int(new_value)) + suffix
+        else:
+            return ("%0.2f" % new_value) + suffix
+    else:
+        return str(value)
+
+
+def get_si_suffix(value):
+    if value >= 10**3:
+        return (10**3, "K")
+    elif value >= 10**6:
+        return (10**6, "M")
+    else:
+        return (1, "")
+
+
+def modify_template(bin_counter, xticklabels, yticklabels, yticks):
+    shutil.copyfile("histogram-large-1d-dataset.template.tex",
+                    "histogram-large-1d-dataset.tex")
+    xticklabels = ", ".join(map(lambda n: "$%s$" % n, xticklabels))
+    yticklabels = ", ".join(yticklabels)
+    yticks = ",".join(yticks)
+    coordinates = ""
+    for i, value in enumerate(bin_counter):
+        coordinates += "(%i, %i) " % (i, value)
+    for line in fileinput.input("histogram-large-1d-dataset.tex",
+                                inplace=True):
+        line = line.replace("{{xticklabels}}", xticklabels)
+        line = line.replace("{{yticklabels}}", yticklabels)
+        line = line.replace("{{yticks}}", yticks)
+        line = line.replace("{{coordinates}}", coordinates)
+        print(line, end='')
+
+
+if __name__ == '__main__':
+    from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
+    parser = ArgumentParser(description=__doc__,
+                            formatter_class=ArgumentDefaultsHelpFormatter)
+    parser.add_argument("-f", "--file", dest="filename",
+                        default="1ddata.txt",
+                        help="use FILE as input data", metavar="FILE")
+    parser.add_argument("-b", "--bins", dest="bins", type=int,
+                        default=15,
+                        help="how many bins should be used")
+    parser.add_argument("-m", "--max", dest="max", type=float,
+                        default=15000,
+                        help=("what is the maximum number "
+                              "that should get binned?"))
+    parser.add_argument("--yticks", dest="yticks", type=int,
+                        default=5,
+                        help=("How many y-ticks should be used?"))
+    args = parser.parse_args()
+    bin_counter, xticklabels, yticklabels, yticks = main(args.filename,
+                                                         args.bins,
+                                                         args.max,
+                                                         args.yticks)
+    modify_template(bin_counter, xticklabels, yticklabels, yticks)