summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2012-05-18graph: q_sum is just sevendayday_windowBenjamin Franzke1-5/+2
2012-05-18document: Put all images into a blockBenjamin Franzke1-0/+4
Or the :: syntax is incorrect and rendering is ugly.
2012-05-18graph: Use font size 9 and fix sevenday axes plotBenjamin Franzke2-9/+9
2012-05-18document.asciidoc: Set latex encoding to utf8 for umlautsBenjamin Franzke1-0/+1
Umlauts in headings are somehow not transformed to latin1.
2012-05-18document: Use ß instead of ss for großBenjamin Franzke1-4/+4
2012-05-18document: Fix some grammarBenjamin Franzke1-2/+2
2012-05-18document: s/ue/ü/Benjamin Franzke1-36/+36
2012-05-18document: s/oe/ö/Benjamin Franzke1-7/+7
2012-05-18document: s/ae/ä/Benjamin Franzke1-23/+23
2012-05-18document: s/liniare/lineare/Benjamin Franzke1-3/+3
2012-05-18graph: Decrease font-size for pdf outputBenjamin Franzke1-2/+2
2012-05-18document: Move a2x instruction to the attribute definitionsBenjamin Franzke1-2/+2
Looks a bit nicer
2012-05-18graph: Add plot and printing of qsum.svgJan Klemkow1-0/+4
2012-05-18doc: Add images for sevenday text block.Jan Klemkow1-3/+2
2012-05-18doc: Add a simple commandline for document.pdf to the MakefileBenjamin Franzke1-0/+3
2012-05-18document (pdf out): Disable revision history and dblatex logoBenjamin Franzke1-0/+2
I wouldn't disable the logo if it wasnt that ugly blurred. We just dont need a revision history.
2012-05-18document: Add language=de and doctype book attributesBenjamin Franzke1-0/+2
Since we want german words for Kapitel, Inhaltsverzeichnis.. Adding doctype=book allows us to omit -d book on commandline.
2012-05-17doc: Fix wrong comment.Jan Klemkow1-2/+2
2012-05-17doc: add vim mode line for asciidoc hightlithingJan Klemkow1-0/+4
2012-05-17doc: Descibe: mean, sevenday, regress time-to-quant, regress fourie.Jan Klemkow1-2/+59
2012-05-17doc: Explain rand/chi prediction.Jan Klemkow1-4/+29
2012-05-14doc: Add opt_pred and sevenday.Jan Klemkow1-0/+36
2012-05-14doc: Fix typoJan Klemkow1-1/+1
2012-05-14doc: Final presentationJan Klemkow1-1/+2
2012-05-14doc: add all errorsJan Klemkow1-2/+3
2012-05-14doc: presenation add other week errorJan Klemkow1-0/+3
2012-05-14regress_frequency_removal: Use logarithmic regressionBenjamin Franzke2-2/+2
2012-05-14doc: presJan Klemkow1-7/+9
2012-05-14doc: WIP presentationJan Klemkow1-7/+19
2012-05-14Add distances to frequency removal regression slideBenjamin Franzke1-0/+1
2012-05-14regress: Add an ugly workaround hack for old octave versionsBenjamin Franzke1-2/+11
2012-05-14Dont return negative quantities in regressionBenjamin Franzke2-0/+2
2012-05-13doc: Describing some methodsJan Klemkow3-18/+72
2012-05-12Add a interval based regressionBenjamin Franzke2-0/+27
But its actually a very ugly prediction.
2012-05-12Explicitly state that price indexes have to correlate with quantitiesBenjamin Franzke1-3/+3
2012-05-12regress_pred: Add degree param, to fold in quad regressionBenjamin Franzke5-29/+10
2012-05-12Fold log_regress_pred into regress_predBenjamin Franzke4-21/+6
By adding a pre-filter function pointer.
2012-05-12Use polyval where appropriateBenjamin Franzke4-20/+8
..instead of doing the polynom multiplication by hand.
2012-05-12Add classification result to .gitignoreBenjamin Franzke1-0/+1
2012-05-12Implement calc_error and total_error as anonymous functionsBenjamin Franzke3-10/+3
2012-05-12get_products: Use better variable namesBenjamin Franzke1-3/+3
2012-05-12get_products: Use reshape to generate the day by product matrixBenjamin Franzke1-14/+2
2012-05-12classify: Print classified table to fileBenjamin Franzke1-1/+13
2012-05-12Add classification scriptBenjamin Franzke1-0/+12
2012-05-12run_tests: Drop random prediction methodJan Klemkow1-1/+1
Verified by: rnd_prod = (method_idx == 6); run_tests; rnd_prod = (rnd_prod & (method_idx == 6)); sum(rnd_prod)
2012-05-12 get_products: Return the real price classification set as wellBenjamin Franzke2-2/+10
2012-05-12Add classification data in octave readable formatBenjamin Franzke1-0/+7980
2012-05-12Add sed script that converts data into octave readable csv filesBenjamin Franzke1-0/+4
Usage: ./gen_octave_input.sed dmc2012_task/train.txt > train_noheader.csv
2012-05-12opt_pred: Split opt_pred in opt_idx and opt_pred.Jan Klemkow3-10/+14
So you can use the idx of opt_idx for other predictions.
2012-05-12Add dmc 2012 official task filesBenjamin Franzke5-0/+32030
generated by cgit (git 2.34.1) at 2024-11-22 01:40:25 +0000