big_ml 0.1.0

data/spec/integration/prediction_spec.rb

@@ -0,0 +1,55 @@
+require "spec_helper"
+
+describe BigML::Prediction, :vcr do
+
+  before(:each) do
+    BigML::Source.delete_all
+    BigML::Dataset.delete_all
+    BigML::Model.delete_all
+    BigML::Prediction.delete_all
+  end
+
+  describe "no prediction" do
+    describe ".all" do
+      it "must be empty" do
+        BigML::Prediction.all.should == []
+      end
+    end
+  end
+
+  describe "one prediction" do
+    before do
+      @source = BigML::Source.create("spec/fixtures/iris.csv")
+      @dataset = BigML::Dataset.create(@source.resource)
+      @model = BigML::Model.create(@dataset.resource)
+      @prediction = BigML::Prediction.create(@model.resource, { :input_data => { "000001" => 3 }})
+    end
+
+    it "was created successfully" do
+      @prediction.code.should == 201
+    end
+
+    it "must have only one item" do 
+      BigML::Prediction.all.should have(1).predictions
+    end
+
+    it "must have the same name" do
+      BigML::Prediction.all.first.name.should == "Prediction for species"
+    end
+
+    it "must be able to be find using the reference" do
+      BigML::Prediction.find(@prediction.id) == @prediction
+    end
+
+    it "must be able to update the name" do
+      BigML::Prediction.update(@prediction.id, { :name => 'foo name' }).code.should == 202
+      BigML::Prediction.find(@prediction.id).name.should == 'foo name'
+    end
+
+    it "must be able to remove the prediction" do
+      BigML::Prediction.delete(@prediction.id)
+      BigML::Prediction.find(@prediction.id).should be_nil
+      BigML::Prediction.all.should have(0).predictions
+    end
+  end
+end

data/spec/integration/source_spec.rb

@@ -0,0 +1,55 @@
+require "spec_helper"
+
+describe BigML::Source, :vcr do
+
+  before(:each) do
+    BigML::Source.all.each do |s|
+      BigML::Source.delete(s.id)
+    end
+    BigML::Dataset.all.each do |s|
+      BigML::Dataset.delete(s.id)
+    end
+  end
+
+  describe "no source" do
+    describe ".all" do
+      it "must be empty" do
+        BigML::Source.all.should == []
+      end
+    end
+  end
+
+  describe "one source" do
+    before do
+      @source = BigML::Source.create("spec/fixtures/iris.csv")
+    end
+
+    it "was created successfully" do
+      @source.code.should == 201
+    end
+
+    it "must have only one item" do 
+      BigML::Source.all.should have(1).sources
+    end
+
+    it "must have the same file_name" do
+      BigML::Source.all.first.file_name.should == "iris.csv"
+    end
+
+    it "must be able to be find using the reference" do
+      BigML::Source.find(@source.id) == @source
+    end
+
+    it "must be able to update the name" do
+      BigML::Source.find(@source.id).name.should == 'iris.csv'
+      BigML::Source.update(@source.id, { :name => 'new name' }).code.should == 202
+      BigML::Source.find(@source.id).name.should == 'new name'
+    end
+
+    it "must be able to remove the source" do
+      BigML::Source.delete(@source.id)
+      BigML::Source.find(@source.id).should be_nil
+      BigML::Source.all.should have(0).sources
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,22 @@
+require 'big_ml'
+require 'rspec'
+require 'vcr'
+
+BigML.configure do |c|
+  c.username = 'foo'
+  c.api_key = 'bar'
+end
+
+VCR.configure do |c|
+  c.cassette_library_dir = 'spec/vcr_cassettes'
+  c.configure_rspec_metadata!
+  c.hook_into :fakeweb
+  c.filter_sensitive_data('<USERNAME>') { BigML.username }
+  c.filter_sensitive_data('<API_KEY>') { BigML.api_key }
+end
+
+
+RSpec.configure do |c|
+  c.mock_with :rspec
+  c.treat_symbols_as_metadata_keys_with_true_values = true
+end

data/spec/units/client_spec.rb

@@ -0,0 +1,50 @@
+require 'spec_helper'
+
+describe BigML::Client do
+  let(:keys) {
+    BigML::Config::VALID_OPTIONS_KEYS
+  }
+
+  context "module configuration" do
+    before(:each) {
+      BigML.configure do |config|
+        keys.each { |key| config.send("#{key}=", key) }
+      end
+    }
+
+    it "should inherit module configuration" do
+      api = BigML::Client.new
+      keys.each { |key| api.send(key).should == key }
+    end
+  end
+
+  context "class configuration" do
+    let(:credentials) {
+      {
+        :username => 'user',
+        :api_key  => 'secret'
+      }
+    }
+
+    context "during initialization" do
+      it "should override module configuration" do
+        api = BigML::Client.new(credentials)
+        keys.each { |key| api.send(key).should == credentials[key] }
+      end
+    end
+
+    context "after initilization" do
+      before(:each) {
+        BigML.configure do |config|
+          keys.each { |key| config.send("#{key}=", key) }
+        end
+      }
+
+      it "should override module configuration" do
+        api = BigML::Client.new
+        credentials.each { |key, value| api.send("#{key}=", value) }
+        keys.each { |key| api.send(key).should == credentials[key] }
+      end
+    end
+  end
+end

data/spec/units/source_spec.rb

@@ -0,0 +1,20 @@
+require "spec_helper"
+
+describe BigML::Source do
+  describe "#code" do
+    it "return code when set" do
+      source = BigML::Source.new('code' => 201)
+      source.code.should == 201
+    end
+
+    it "return nil when not set" do
+      source = BigML::Source.new('code' => nil)
+      source.code.should be_nil
+    end
+
+    it "extract source id from resource" do
+      source = BigML::Source.new('resource' => 'souce/4f66a0b903ce8940c5000000')
+      source.id.should == "4f66a0b903ce8940c5000000"
+    end
+  end
+end

data/spec/vcr_cassettes/BigML_Dataset/no_dataset/_all/must_be_empty.yml

@@ -0,0 +1,136 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/source?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:18 GMT
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '1280'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"meta": {"limit": 20, "next": null, "offset": 0, "previous": null,
+        "total_count": 1}, "objects": [{"category": 0, "code": 200, "content_type":
+        "application/octet-stream", "created": "2012-06-20T03:49:33.139000", "credits":
+        0.0, "description": "", "fields": {"000000": {"column_number": 0, "name":
+        "sepal length", "optype": "numeric"}, "000001": {"column_number": 1, "name":
+        "sepal width", "optype": "numeric"}, "000002": {"column_number": 2, "name":
+        "petal length", "optype": "numeric"}, "000003": {"column_number": 3, "name":
+        "petal width", "optype": "numeric"}, "000004": {"column_number": 4, "name":
+        "species", "optype": "categorical"}}, "file_name": "iris.csv", "md5": "d1175c032e1042bec7f974c91e4a65ae",
+        "name": "iris.csv", "number_of_datasets": 0, "number_of_models": 0, "number_of_predictions":
+        0, "private": true, "resource": "source/4fe1484d035d074a1e0000f1", "size":
+        4608, "source_parser": {"header": true, "locale": "en_US", "missing_tokens":
+        ["", "N/A", "n/a", "NULL", "null", "-", "#DIV/0", "#REF!", "#NAME?", "NIL",
+        "nil", "NA", "na", "#VALUE!", "#NULL!", "NaN", "#N/A", "#NUM!", "?"], "quote":
+        "\"", "separator": ","}, "status": {"code": 5, "elapsed": 69, "message": "The
+        source has been created"}, "tags": [], "type": 0, "updated": "2012-06-20T03:49:33.160000"}]}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:09 GMT
+- request:
+    method: delete
+    uri: https://bigml.io/andromeda/source/4fe1484d035d074a1e0000f1?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 204
+      message: NO CONTENT
+    headers:
+      content-length:
+      - '0'
+      content-type:
+      - text/html; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:54:40 GMT
+      server:
+      - nginx/1.0.12
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ''
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:11 GMT
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/dataset?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:22 GMT
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '101'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"meta": {"limit": 20, "next": null, "offset": 0, "previous": null,
+        "total_count": 0}, "objects": []}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:12 GMT
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/dataset?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:54:42 GMT
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '101'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"meta": {"limit": 20, "next": null, "offset": 0, "previous": null,
+        "total_count": 0}, "objects": []}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:13 GMT
+recorded_with: VCR 2.2.2

data/spec/vcr_cassettes/BigML_Dataset/one_dataset/must_be_able_to_be_find_using_the_reference.yml

@@ -0,0 +1,293 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/source?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:46 GMT
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '1281'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"meta": {"limit": 20, "next": null, "offset": 0, "previous": null,
+        "total_count": 1}, "objects": [{"category": 0, "code": 200, "content_type":
+        "application/octet-stream", "created": "2012-06-20T03:56:50.608000", "credits":
+        0.0, "description": "", "fields": {"000000": {"column_number": 0, "name":
+        "sepal length", "optype": "numeric"}, "000001": {"column_number": 1, "name":
+        "sepal width", "optype": "numeric"}, "000002": {"column_number": 2, "name":
+        "petal length", "optype": "numeric"}, "000003": {"column_number": 3, "name":
+        "petal width", "optype": "numeric"}, "000004": {"column_number": 4, "name":
+        "species", "optype": "categorical"}}, "file_name": "iris.csv", "md5": "d1175c032e1042bec7f974c91e4a65ae",
+        "name": "iris.csv", "number_of_datasets": 1, "number_of_models": 0, "number_of_predictions":
+        0, "private": true, "resource": "source/4fe14a021552687d42000136", "size":
+        4608, "source_parser": {"header": true, "locale": "en_US", "missing_tokens":
+        ["", "N/A", "n/a", "NULL", "null", "-", "#DIV/0", "#REF!", "#NAME?", "NIL",
+        "nil", "NA", "na", "#VALUE!", "#NULL!", "NaN", "#N/A", "#NUM!", "?"], "quote":
+        "\"", "separator": ","}, "status": {"code": 5, "elapsed": 100, "message":
+        "The source has been created"}, "tags": [], "type": 0, "updated": "2012-06-20T03:56:23.639000"}]}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:37 GMT
+- request:
+    method: delete
+    uri: https://bigml.io/andromeda/source/4fe14a021552687d42000136?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 204
+      message: NO CONTENT
+    headers:
+      content-length:
+      - '0'
+      content-type:
+      - text/html; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:55:07 GMT
+      server:
+      - nginx/1.0.12
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ''
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:38 GMT
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/dataset?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:49 GMT
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '703'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"meta": {"limit": 20, "next": null, "offset": 0, "previous": null,
+        "total_count": 1}, "objects": [{"category": 0, "code": 200, "columns": 5,
+        "created": "2012-06-20T03:56:23.634000", "credits": 0.0087890625, "description":
+        "", "locale": "en_US", "name": "iris'' dataset", "number_of_models": 0, "number_of_predictions":
+        0, "private": true, "resource": "dataset/4fe149e7035d074a21000141", "rows":
+        150, "size": 4608, "source": "source/4fe14a021552687d42000136", "source_status":
+        false, "status": {"bytes": 4608, "code": 5, "elapsed": 107, "field_errors":
+        [], "message": "The dataset has been created", "row_format_errors": [], "serialized_rows":
+        150}, "tags": [], "updated": "2012-06-20T03:56:24.895000"}]}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:39 GMT
+- request:
+    method: delete
+    uri: https://bigml.io/andromeda/dataset/4fe149e7035d074a21000141?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 204
+      message: NO CONTENT
+    headers:
+      content-length:
+      - '0'
+      content-type:
+      - text/html; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:55:10 GMT
+      server:
+      - nginx/1.0.12
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ''
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:41 GMT
+- request:
+    method: post
+    uri: https://bigml.io/andromeda/source
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      content-type:
+      - multipart/form-data; boundary=-----------RubyMultipartPost
+      content-length:
+      - '5147'
+      connection:
+      - close
+  response:
+    status:
+      code: 201
+      message: CREATED
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:52 GMT
+      location:
+      - http://bigml.io/andromeda/source/4fe14a0b1552687d4200013a
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '567'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"category": 0, "code": 201, "content_type": "application/octet-stream",
+        "created": "2012-06-20T03:56:59.857540", "credits": 0.0, "description": "",
+        "file_name": "iris.csv", "md5": "d1175c032e1042bec7f974c91e4a65ae", "name":
+        "iris.csv", "number_of_datasets": 0, "number_of_models": 0, "number_of_predictions":
+        0, "private": true, "resource": "source/4fe14a0b1552687d4200013a", "size":
+        4608, "source_parser": {}, "status": {"code": 1, "message": "The request has
+        been queued and will be processed soon"}, "tags": [], "type": 0, "updated":
+        "2012-06-20T03:56:59.857561"}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:43 GMT
+- request:
+    method: post
+    uri: https://bigml.io/andromeda/dataset?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: UTF-8
+      string: ! '{"source":"source/4fe14a0b1552687d4200013a"}'
+    headers:
+      content-type:
+      - application/json
+      connection:
+      - close
+  response:
+    status:
+      code: 201
+      message: CREATED
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:55:14 GMT
+      location:
+      - http://bigml.io/andromeda/dataset/4fe14a0d1552687d480000fa
+      server:
+      - nginx/1.0.12
+      content-length:
+      - '920'
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"category": 0, "code": 201, "columns": 5, "created": "2012-06-20T03:57:01.914340",
+        "credits": 0.0087890625, "description": "", "fields": {"000000": {"column_number":
+        0, "name": "sepal length", "optype": "numeric"}, "000001": {"column_number":
+        1, "name": "sepal width", "optype": "numeric"}, "000002": {"column_number":
+        2, "name": "petal length", "optype": "numeric"}, "000003": {"column_number":
+        3, "name": "petal width", "optype": "numeric"}, "000004": {"column_number":
+        4, "name": "species", "optype": "categorical"}}, "locale": "en_US", "name":
+        "iris'' dataset", "number_of_models": 0, "number_of_predictions": 0, "private":
+        true, "resource": "dataset/4fe14a0d1552687d480000fa", "rows": 0, "size": 4608,
+        "source": "source/4fe14a0b1552687d4200013a", "source_status": true, "status":
+        {"code": 1, "message": "The dataset is being processed and will be created
+        soon"}, "tags": [], "updated": "2012-06-20T03:57:01.914358"}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:45 GMT
+- request:
+    method: get
+    uri: https://bigml.io/andromeda/dataset/4fe14a0d1552687d480000fa?username=<USERNAME>&api_key=<API_KEY>
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      connection:
+      - close
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      content-type:
+      - application/json; charset=utf-8
+      date:
+      - Wed, 20 Jun 2012 03:52:55 GMT
+      server:
+      - nginx/1.0.12
+      transfer-encoding:
+      - chunked
+      connection:
+      - Close
+    body:
+      encoding: US-ASCII
+      string: ! '{"category": 0, "code": 200, "columns": 5, "created": "2012-06-20T03:57:01.914000",
+        "credits": 0.0087890625, "description": "", "fields": {"000000": {"column_number":
+        0, "datatype": "double", "name": "sepal length", "optype": "numeric", "preferred":
+        true, "summary": {"maximum": 7.9, "median": 5.77889, "minimum": 4.3, "missing_count":
+        0, "population": 150, "splits": [4.51526, 4.67252, 4.81113, 4.89582, 4.96139,
+        5.01131, 5.05992, 5.11148, 5.18177, 5.35681, 5.44129, 5.5108, 5.58255, 5.65532,
+        5.71658, 5.77889, 5.85381, 5.97078, 6.05104, 6.13074, 6.23023, 6.29578, 6.35078,
+        6.41459, 6.49383, 6.63013, 6.70719, 6.79218, 6.92597, 7.20423, 7.64746], "sum":
+        876.5, "sum_squares": 5223.85}}, "000001": {"column_number": 1, "datatype":
+        "double", "name": "sepal width", "optype": "numeric", "preferred": true, "summary":
+        {"counts": [[2, 1], [2.2, 3], [2.3, 4], [2.4, 3], [2.5, 8], [2.6, 5], [2.7,
+        9], [2.8, 14], [2.9, 10], [3, 26], [3.1, 11], [3.2, 13], [3.3, 6], [3.4, 12],
+        [3.5, 6], [3.6, 4], [3.7, 3], [3.8, 6], [3.9, 2], [4, 1], [4.1, 1], [4.2,
+        1], [4.4, 1]], "maximum": 4.4, "median": 3.02044, "minimum": 2, "missing_count":
+        0, "population": 150, "sum": 458.6, "sum_squares": 1430.4}}, "000002": {"column_number":
+        2, "datatype": "double", "name": "petal length", "optype": "numeric", "preferred":
+        true, "summary": {"maximum": 6.9, "median": 4.34142, "minimum": 1, "missing_count":
+        0, "population": 150, "splits": [1.25138, 1.32426, 1.37171, 1.40962, 1.44567,
+        1.48173, 1.51859, 1.56301, 1.6255, 1.74645, 3.23033, 3.675, 3.94203, 4.0469,
+        4.18243, 4.34142, 4.45309, 4.51823, 4.61771, 4.72566, 4.83445, 4.93363, 5.03807,
+        5.1064, 5.20938, 5.43979, 5.5744, 5.6646, 5.81496, 6.02913, 6.38125], "sum":
+        563.7, "sum_squares": 2582.71}}, "000003": {"column_number": 3, "datatype":
+        "double", "name": "petal width", "optype": "numeric", "preferred": true, "summary":
+        {"counts": [[0.1, 5], [0.2, 29], [0.3, 7], [0.4, 7], [0.5, 1], [0.6, 1], [1,
+        7], [1.1, 3], [1.2, 5], [1.3, 13], [1.4, 8], [1.5, 12], [1.6, 4], [1.7, 2],
+        [1.8, 12], [1.9, 5], [2, 6], [2.1, 6], [2.2, 3], [2.3, 8], [2.4, 3], [2.5,
+        3]], "maximum": 2.5, "median": 1.32848, "minimum": 0.1, "missing_count": 0,
+        "population": 150, "sum": 179.9, "sum_squares": 302.33}}, "000004": {"column_number":
+        4, "datatype": "string", "name": "species", "optype": "categorical", "preferred":
+        true, "summary": {"categories": [["Iris-versicolor", 50], ["Iris-setosa",
+        50], ["Iris-virginica", 50]], "missing_count": 0}}}, "locale": "en_US", "name":
+        "iris'' dataset", "number_of_models": 0, "number_of_predictions": 0, "private":
+        true, "resource": "dataset/4fe14a0d1552687d480000fa", "rows": 150, "size":
+        4608, "source": "source/4fe14a0b1552687d4200013a", "source_status": true,
+        "status": {"bytes": 4608, "code": 5, "elapsed": 846, "field_errors": [], "message":
+        "The dataset has been created", "row_format_errors": [], "serialized_rows":
+        150}, "tags": [], "updated": "2012-06-20T03:57:01.995000"}'
+    http_version: '1.1'
+  recorded_at: Wed, 20 Jun 2012 03:56:46 GMT
+recorded_with: VCR 2.2.2