Run clmfmt fix on examples folder (#261)

Co-authored-by: Anthony Khong <[email protected]>
zero-one-group · Oct 13, 2020 · f30c6d3 · f30c6d3
1 parent 0adf6ae
commit f30c6d3
Show file tree

Hide file tree

Showing 15 changed files with 193 additions and 199 deletions.
diff --git a/examples/classification.clj b/examples/classification.clj
@@ -1,7 +1,7 @@
 (ns examples.classification
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.ml :as ml]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.ml :as ml]))
 
 ;; Logistic Regression
 (def training (g/read-libsvm! "test/resources/sample_libsvm_data.txt"))
@@ -52,15 +52,15 @@
 
 (def pipeline
   (ml/pipeline
-    label-indexer
-    feature-indexer
-    (ml/gbt-classifier {:label-col :indexed-label
-                        :features-col :indexed-features
-                        :max-iter 10
-                        :feature-subset-strategy "auto"})
-    (ml/index-to-string {:input-col :prediction
-                         :output-col :predicted-label
-                         :labels (.labels label-indexer)})))
+   label-indexer
+   feature-indexer
+   (ml/gbt-classifier {:label-col :indexed-label
+                       :features-col :indexed-features
+                       :max-iter 10
+                       :feature-subset-strategy "auto"})
+   (ml/index-to-string {:input-col :prediction
+                        :output-col :predicted-label
+                        :labels (.labels label-indexer)})))
 
 (def model (ml/fit train-data pipeline))
 

diff --git a/examples/clustering.clj b/examples/clustering.clj
@@ -1,7 +1,7 @@
 (ns examples.clustering
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.ml :as ml]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.ml :as ml]))
 
 ;; K-Means
 (def dataset
@@ -38,15 +38,14 @@
     (ml/transform model)
     (g/limit 2)
     (g/collect-col :topicDistribution))
-#_
-((0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0)
- (0.07537574948606664
-  0.07537608757379946
-  0.07537444990446238
-  0.0753760406513953
-  0.32162508215023483
-  0.07537597087758716
-  0.0753743398006919
-  0.0753743698147718
-  0.075374842014245
-  0.07537306772674557))
+#_((0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0)
+   (0.07537574948606664
+    0.07537608757379946
+    0.07537444990446238
+    0.0753760406513953
+    0.32162508215023483
+    0.07537597087758716
+    0.0753743398006919
+    0.0753743698147718
+    0.075374842014245
+    0.07537306772674557))
diff --git a/examples/customer_segmentation.clj b/examples/customer_segmentation.clj
@@ -45,11 +45,11 @@
   (-> invoices
       (g/remove (g/null? :description))
       (ml/transform
-        (ml/tokeniser {:input-col  :description
-                       :output-col :descriptors}))
+       (ml/tokeniser {:input-col  :description
+                      :output-col :descriptors}))
       (ml/transform
-        (ml/stop-words-remover {:input-col  :descriptors
-                                :output-col :cleaned-descriptors}))
+       (ml/stop-words-remover {:input-col  :descriptors
+                               :output-col :cleaned-descriptors}))
       (g/with-column :descriptor (g/explode :cleaned-descriptors))
       (g/with-column :descriptor (g/regexp-replace :descriptor
                                                    (g/lit "[^a-zA-Z'']")
@@ -84,9 +84,9 @@
 (def log-spending
   (-> descriptors
       (g/remove (g/||
-                  (g/null? :customer-id)
-                  (g/< :price 0.01)
-                  (g/< :quantity 1)))
+                 (g/null? :customer-id)
+                 (g/< :price 0.01)
+                 (g/< :quantity 1)))
       (g/group-by :customer-id :descriptor)
       (g/agg {:log-spend (g/log1p (g/sum (g/* :price :quantity)))})
       (g/order-by (g/desc :log-spend))))
@@ -104,24 +104,24 @@
 
 (def nmf-pipeline
   (ml/pipeline
-    (ml/string-indexer {:input-col  :descriptor
-                        :output-col :descriptor-id})
-    (ml/als {:max-iter    100
-             :reg-param   0.01
-             :rank        8
-             :nonnegative true
-             :user-col    :customer-id
-             :item-col    :descriptor-id
-             :rating-col  :log-spend})))
+   (ml/string-indexer {:input-col  :descriptor
+                       :output-col :descriptor-id})
+   (ml/als {:max-iter    100
+            :reg-param   0.01
+            :rank        8
+            :nonnegative true
+            :user-col    :customer-id
+            :item-col    :descriptor-id
+            :rating-col  :log-spend})))
 
 (def nmf-pipeline-model
   (ml/fit log-spending nmf-pipeline))
 
 (def id->descriptor
   (ml/index-to-string
-    {:input-col  :id
-     :output-col :descriptor
-     :labels     (ml/labels (first (ml/stages nmf-pipeline-model)))}))
+   {:input-col  :id
+    :output-col :descriptor
+    :labels     (ml/labels (first (ml/stages nmf-pipeline-model)))}))
 
 (def nmf-model (last (ml/stages nmf-pipeline-model)))
 

diff --git a/examples/dataframe_api.clj b/examples/dataframe_api.clj
@@ -1,7 +1,7 @@
 (ns examples.dataframe-api
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.test-resources :refer [melbourne-df]]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.test-resources :refer [melbourne-df]]))
 
 (def dataframe melbourne-df)
 

diff --git a/examples/features.clj b/examples/features.clj
@@ -1,26 +1,26 @@
 (ns examples.features
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.ml :as ml]
-    [zero-one.geni.test-resources :refer [libsvm-df]]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.ml :as ml]
+   [zero-one.geni.test-resources :refer [libsvm-df]]))
 
 ;; Tokeniser, Hashing TF and IDF
 (def sentence-data
   (g/table->dataset
-    [[0.0 "Hi I heard about Spark"]
-     [0.0 "I wish Java could use case classes"]
-     [1.0 "Logistic regression models are neat"]]
-    [:label :sentence]))
+   [[0.0 "Hi I heard about Spark"]
+    [0.0 "I wish Java could use case classes"]
+    [1.0 "Logistic regression models are neat"]]
+   [:label :sentence]))
 
 (def pipeline
   (ml/pipeline
-    (ml/tokenizer {:input-col :sentence
-                    :output-col :words})
-    (ml/hashing-tf {:num-features 20
-                    :input-col :words
-                    :output-col :raw-features})
-    (ml/idf {:input-col :raw-features
-              :output-col :features})))
+   (ml/tokenizer {:input-col :sentence
+                  :output-col :words})
+   (ml/hashing-tf {:num-features 20
+                   :input-col :words
+                   :output-col :raw-features})
+   (ml/idf {:input-col :raw-features
+            :output-col :features})))
 
 (def pipeline-model
   (ml/fit sentence-data pipeline))
@@ -30,22 +30,21 @@
     (g/collect-col :features))
 
 ;;=>
-#_
-((0.28768207245178085
-  0.6931471805599453
-  0.28768207245178085
-  0.5753641449035617)
- (0.6931471805599453
-  0.6931471805599453
-  1.3862943611198906
-  0.28768207245178085
-  0.6931471805599453
-  0.28768207245178085)
- (0.6931471805599453
-  0.6931471805599453
-  0.28768207245178085
-  0.6931471805599453
-  0.6931471805599453))
+#_((0.28768207245178085
+    0.6931471805599453
+    0.28768207245178085
+    0.5753641449035617)
+   (0.6931471805599453
+    0.6931471805599453
+    1.3862943611198906
+    0.28768207245178085
+    0.6931471805599453
+    0.28768207245178085)
+   (0.6931471805599453
+    0.6931471805599453
+    0.28768207245178085
+    0.6931471805599453
+    0.6931471805599453))
 
 ;; PCA
 (def dataframe
@@ -65,10 +64,9 @@
     (g/collect-col :pca-features))
 
 ;;=>
-#_
-((1.6485728230883814 -4.0132827005162985 -1.0091435193998504)
- (-4.645104331781533 -1.1167972663619048 -1.0091435193998501)
- (-6.428880535676488 -5.337951427775359 -1.009143519399851))
+#_((1.6485728230883814 -4.0132827005162985 -1.0091435193998504)
+   (-4.645104331781533 -1.1167972663619048 -1.0091435193998501)
+   (-6.428880535676488 -5.337951427775359 -1.009143519399851))
 
 ;; Standard Scaler
 (def scaler

diff --git a/examples/foreign_idioms.clj b/examples/foreign_idioms.clj
@@ -1,7 +1,7 @@
 (ns examples.foreign-idioms
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.test-resources :refer [melbourne-df]]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.test-resources :refer [melbourne-df]]))
 
 (def dataframe melbourne-df)
 

diff --git a/examples/frequent_pattern.clj b/examples/frequent_pattern.clj
@@ -1,14 +1,14 @@
 (ns examples.classification
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.ml :as ml]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.ml :as ml]))
 
 (def dataset
   (-> (g/table->dataset
-        [['("1" "2" "5")]
-         ['("1" "2" "3" "5")]
-         ['("1" "2")]]
-        [:items])))
+       [['("1" "2" "5")]
+        ['("1" "2" "3" "5")]
+        ['("1" "2")]]
+       [:items])))
 
 (def model
   (ml/fit

diff --git a/examples/model_selection.clj b/examples/model_selection.clj
@@ -1,23 +1,23 @@
 (ns examples.classification
   (:require
-    [zero-one.geni.core :as g]
-    [zero-one.geni.ml :as ml]))
+   [zero-one.geni.core :as g]
+   [zero-one.geni.ml :as ml]))
 
 (def training
   (g/table->dataset
-    [[0  "a b c d e spark"  1.0]
-     [1  "b d"              0.0]
-     [2  "spark f g h"      1.0]
-     [3  "hadoop mapreduce" 0.0]
-     [4  "b spark who"      1.0]
-     [5  "g d a y"          0.0]
-     [6  "spark fly"        1.0]
-     [7  "was mapreduce"    0.0]
-     [8  "e spark program"  1.0]
-     [9  "a e c l"          0.0]
-     [10 "spark compile"    1.0]
-     [11 "hadoop software"  0.0]]
-    [:id :text :label]))
+   [[0  "a b c d e spark"  1.0]
+    [1  "b d"              0.0]
+    [2  "spark f g h"      1.0]
+    [3  "hadoop mapreduce" 0.0]
+    [4  "b spark who"      1.0]
+    [5  "g d a y"          0.0]
+    [6  "spark fly"        1.0]
+    [7  "was mapreduce"    0.0]
+    [8  "e spark program"  1.0]
+    [9  "a e c l"          0.0]
+    [10 "spark compile"    1.0]
+    [11 "hadoop software"  0.0]]
+   [:id :text :label]))
 
 (def hashing-tf
   (ml/hashing-tf {:input-col :words :output-col :features}))
@@ -27,14 +27,14 @@
 
 (def pipeline
   (ml/pipeline
-    (ml/tokeniser {:input-col :text :output-col :words})
-    hashing-tf
-    logistic-reg))
+   (ml/tokeniser {:input-col :text :output-col :words})
+   hashing-tf
+   logistic-reg))
 
 (def param-grid
   (ml/param-grid
-    {hashing-tf {:num-features (mapv int [10 100 1000])}
-     logistic-reg {:reg-param [0.1 0.01]}}))
+   {hashing-tf {:num-features (mapv int [10 100 1000])}
+    logistic-reg {:reg-param [0.1 0.01]}}))
 
 (def cross-validator
   (ml/cross-validator {:estimator pipeline
@@ -59,20 +59,19 @@
     g/collect)
 
 ;;=>
-#_
-({:id 4,
-  :text "spark i j k",
-  :probability (1.994512925146874E-4 0.9998005487074854),
-  :prediction 1.0}
- {:id 5,
-  :text "l m n",
-  :probability (0.9326577483128498 0.06734225168715033),
-  :prediction 0.0}
- {:id 6,
-  :text "mapreduce spark",
-  :probability (0.5561018462768792 0.4438981537231208),
-  :prediction 0.0}
- {:id 7,
-  :text "apache hadoop",
-  :probability (0.9488612611950926 0.051138738804907484),
-  :prediction 0.0})
+#_({:id 4,
+    :text "spark i j k",
+    :probability (1.994512925146874E-4 0.9998005487074854),
+    :prediction 1.0}
+   {:id 5,
+    :text "l m n",
+    :probability (0.9326577483128498 0.06734225168715033),
+    :prediction 0.0}
+   {:id 6,
+    :text "mapreduce spark",
+    :probability (0.5561018462768792 0.4438981537231208),
+    :prediction 0.0}
+   {:id 7,
+    :text "apache hadoop",
+    :probability (0.9488612611950926 0.051138738804907484),
+    :prediction 0.0})