| rm -f tags | |
| python setup.py clean | |
| running clean | |
| removing 'build/temp.macosx-10.7-x86_64-3.6' (and everything under it) | |
| removing 'build' | |
| Partial import of sklearn during the build process. | |
| Will remove generated .c files | |
| rm -rf dist | |
| python setup.py build_ext -i | |
| blas_opt_info: |
| package org.apache.spark.sql.types | |
| import xxx.Condition | |
| import xxx.Department | |
| class ConditionUDT extends UserDefinedType[Condition.Value] { | |
| override def sqlType: DataType = IntegerType | |
| override def serialize(obj: Condition.Value): Int = obj.id |
| """Information Retrieval metrics | |
| Useful Resources: | |
| http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt | |
| http://www.nii.ac.jp/TechReports/05-014E.pdf | |
| http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf | |
| http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf | |
| Learning to Rank for Information Retrieval (Tie-Yan Liu) | |
| """ | |
| import numpy as np |
| fig, ax = plt.subplots(nrows=2, ncols=3) | |
| perplexity = [[2, 10, 20], | |
| [30, 50, 100]] | |
| iterations = [[1000, 1000, 1000], | |
| [1000, 1000, 1000]] | |
| for ri, row in enumerate(ax): | |
| for ci, col in enumerate(row): |
| from tempfile import NamedTemporaryFile | |
| import base64 | |
| def inline_hist(data, figsize=(4, 4), **kwags): | |
| data = list(data) | |
| fig, ax = plt.subplots(1, 1, figsize=figsize, **kwags) | |
| for k,v in ax.spines.items(): | |
| v.set_visible(False) |
| import static java.lang.Math.sqrt; | |
| public class S { | |
| public static void main(String[] args) { | |
| int[][] s = createSpiral(20); | |
| print(s); | |
| } | |
| private static int[][] createSpiral(int n) { |
| import scipy.stats | |
| import numpy as np | |
| n = 200 | |
| s = scipy.stats.randint.rvs(0, n, size = 2) | |
| X = scipy.stats.randint.rvs(0, n, size = s[0] * 2 + 1) | |
| Y = scipy.stats.randint.rvs(0, n, size = s[1] * 2) | |
| i = 1 |
A checklist for designing and developing internet scale services, inspired by James Hamilton's 2007 paper "On Desgining and Deploying Internet-Scale Services."