I have a dataset but I would like to append more information onto it to make it more useful. In data warehousing this is similar to the concept of creating dimensions. With dimensional aka dim you can do this from the command line or in an iPython notebook.
Here's how it works.
pip install dimensional - this installs a cli called dim
| from flask import Flask, request, abort, jsonify | |
| from sklearn.externals import joblib | |
| import numpy as np | |
| app = Flask(__name__) | |
| # Treat model like a backing resource that can be changed out with and ENV variable. | |
| MODEL_FILE = 'model/iris_classifier.pkl' | |
| CLASSES = ['setosa', |
| brew install rbenv ruby-build | |
| echo 'export PATH=$HOME/.rbenv/bin:$PATH | |
| echo 'eval "$(rbenv init -)"' >> .zshrc | |
| source .zshrc | |
| rbenv install -l | |
| rbenv install x.x.x | |
| rbenv rehash |
| class Dataset(object): | |
| name = None | |
| source_url = None | |
| processing_notes = None # What modifications to the original data set were done. Outliers, Imputation, etc? | |
| license = None # Something about how this can be used CC/Apache/etc. | |
| columns = [] | |
| def __str__(self): |
| -- MySQL dump 10.9 | |
| -- | |
| -- Host: localhost Database: world | |
| -- ------------------------------------------------------ | |
| -- Server version 4.1.13-log | |
| /*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */; | |
| /*!40101 SET @OLD_CHARACTER_SET_RESULTS=@@CHARACTER_SET_RESULTS */; | |
| /*!40101 SET @OLD_COLLATION_CONNECTION=@@COLLATION_CONNECTION */; | |
| /*!40101 SET NAMES latin1 */; |
| CREATE TABLE "public"."times" ( | |
| id int4 NOT NULL, | |
| time time, | |
| hour int2, | |
| military_hour int2, | |
| minute int4, | |
| second int4, | |
| minute_of_day int4, | |
| second_of_day int4, | |
| quarter_hour varchar, |
| CREATE TABLE public.dates ( | |
| id int4 NOT NULL PRIMARY KEY, | |
| date date NOT NULL, | |
| datetime timestamp NOT NULL, | |
| julian_day int4 NOT NULL, | |
| day int4 NOT NULL, | |
| day_name varchar NOT NULL, | |
| day_abbrev varchar NOT NULL, |
| Thing I want to do | Command |
|---|---|
| overwrite file | > |
| append to file | >> |
| search in file | grep '??' file.csv |
| search in file (case insensitive) | grep 'LLC' -i file.csv |
| search in file (show line numbers) | grep ',llc,' -n file.csv |
| remove header | tail -n +2 file.csv > new_file.csv |
| remove header | sed 1d file.csv > new_file.csv |
| add header | { head -1 with_header.csv; cat headerless.csv;} > new_file.csv |
| -- Many-to-many table schema for users and favorites | |
| CREATE TABLE `user_favorites` ( | |
| `id` int(11) unsigned NOT NULL AUTO_INCREMENT, | |
| `user_id` int(11) DEFAULT NULL, | |
| `deal_id` int(11) DEFAULT NULL, | |
| `created_date` datetime DEFAULT CURRENT_TIMESTAMP, | |
| PRIMARY KEY (`id`) | |
| ) ENGINE=InnoDB AUTO_INCREMENT=33 DEFAULT CHARSET=utf8; |