Google-Cloud-Labs-Solutions/Predict Visitor Purchases with a Classification Model in BigQuery ML at main · Dev-tanay/Google-Cloud-Labs-Solutions · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
// Run this in cloudshell //

bq mk ecommerce
bq query --nouse_legacy_sql '
CREATE OR REPLACE MODEL `ecommerce.classification_model`
OPTIONS
(
model_type="logistic_reg",
labels = ["will_buy_on_return_visit"]
)
AS
#standardSQL
SELECT
  * EXCEPT(fullVisitorId)
FROM
  # features
  (SELECT
    fullVisitorId,
    IFNULL(totals.bounces, 0) AS bounces,
    IFNULL(totals.timeOnSite, 0) AS time_on_site
  FROM
    `data-to-insights.ecommerce.web_analytics`
  WHERE
    totals.newVisits = 1
    AND date BETWEEN "20160801" AND "20170430") # train on first 9 months
  JOIN
  (SELECT
    fullvisitorid,
    IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit
  FROM
      `data-to-insights.ecommerce.web_analytics`
  GROUP BY fullvisitorid)
  USING (fullVisitorId);'
bq query --nouse_legacy_sql '
SELECT
  roc_auc,
  CASE
    WHEN roc_auc > .9 THEN "good"
    WHEN roc_auc > .8 THEN "fair"
    WHEN roc_auc > .7 THEN "decent"
    WHEN roc_auc > .6 THEN "not great"
  ELSE "poor" END AS model_quality
FROM
  ML.EVALUATE(MODEL ecommerce.classification_model,  (
SELECT
  * EXCEPT(fullVisitorId)
FROM
  # features
  (SELECT
    fullVisitorId,
    IFNULL(totals.bounces, 0) AS bounces,
    IFNULL(totals.timeOnSite, 0) AS time_on_site
  FROM
    `data-to-insights.ecommerce.web_analytics`
  WHERE
    totals.newVisits = 1
    AND date BETWEEN "20170501" AND "20170630") # eval on 2 months
  JOIN
  (SELECT
    fullvisitorid,
    IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit
  FROM
      `data-to-insights.ecommerce.web_analytics`
  GROUP BY fullvisitorid)
  USING (fullVisitorId)
));'
bq query --nouse_legacy_sql '
CREATE OR REPLACE MODEL `ecommerce.classification_model_2`
OPTIONS
  (model_type="logistic_reg", labels = ["will_buy_on_return_visit"]) AS
WITH all_visitor_stats AS (
SELECT
  fullvisitorid,
  IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit
  FROM `data-to-insights.ecommerce.web_analytics`
  GROUP BY fullvisitorid
)
# add in new features
SELECT * EXCEPT(unique_session_id) FROM (
  SELECT
      CONCAT(fullvisitorid, CAST(visitId AS STRING)) AS unique_session_id,
      # labels
      will_buy_on_return_visit,
      MAX(CAST(h.eCommerceAction.action_type AS INT64)) AS latest_ecommerce_progress,
      # behavior on the site
      IFNULL(totals.bounces, 0) AS bounces,
      IFNULL(totals.timeOnSite, 0) AS time_on_site,
      IFNULL(totals.pageviews, 0) AS pageviews,
      # where the visitor came from
      trafficSource.source,
      trafficSource.medium,
      channelGrouping,
      # mobile or desktop
      device.deviceCategory,
      # geographic
      IFNULL(geoNetwork.country, "") AS country
  FROM `data-to-insights.ecommerce.web_analytics`,
     UNNEST(hits) AS h
    JOIN all_visitor_stats USING(fullvisitorid)
  WHERE 1=1
    # only predict for new visits
    AND totals.newVisits = 1
    AND date BETWEEN "20160801" AND "20170430" # train 9 months
  GROUP BY
  unique_session_id,
  will_buy_on_return_visit,
  bounces,
  time_on_site,
  totals.pageviews,
  trafficSource.source,
  trafficSource.medium,
  channelGrouping,
  device.deviceCategory,
  country
);'
bq query --nouse_legacy_sql '
#standardSQL
SELECT
  roc_auc,
  CASE
    WHEN roc_auc > .9 THEN "good"
    WHEN roc_auc > .8 THEN "fair"
    WHEN roc_auc > .7 THEN "decent"
    WHEN roc_auc > .6 THEN "not great"
  ELSE "poor" END AS model_quality
FROM
  ML.EVALUATE(MODEL ecommerce.classification_model_2,  (
WITH all_visitor_stats AS (
SELECT
  fullvisitorid,
  IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit
  FROM `data-to-insights.ecommerce.web_analytics`
  GROUP BY fullvisitorid
)
# add in new features
SELECT * EXCEPT(unique_session_id) FROM (
  SELECT
      CONCAT(fullvisitorid, CAST(visitId AS STRING)) AS unique_session_id,
      # labels
      will_buy_on_return_visit,
      MAX(CAST(h.eCommerceAction.action_type AS INT64)) AS latest_ecommerce_progress,
      # behavior on the site
      IFNULL(totals.bounces, 0) AS bounces,
      IFNULL(totals.timeOnSite, 0) AS time_on_site,
      totals.pageviews,
      # where the visitor came from
      trafficSource.source,
      trafficSource.medium,
      channelGrouping,
      # mobile or desktop
      device.deviceCategory,
      # geographic
      IFNULL(geoNetwork.country, "") AS country
  FROM `data-to-insights.ecommerce.web_analytics`,
     UNNEST(hits) AS h
    JOIN all_visitor_stats USING(fullvisitorid)
  WHERE 1=1
    # only predict for new visits
    AND totals.newVisits = 1
    AND date BETWEEN "20170501" AND "20170630" # eval 2 months
  GROUP BY
  unique_session_id,
  will_buy_on_return_visit,
  bounces,
  time_on_site,
  totals.pageviews,
  trafficSource.source,
  trafficSource.medium,
  channelGrouping,
  device.deviceCategory,
  country
)
));'
bq query --nouse_legacy_sql '
SELECT
*
FROM
  ml.PREDICT(MODEL `ecommerce.classification_model_2`,
   (
WITH all_visitor_stats AS (
SELECT
  fullvisitorid,
  IF(COUNTIF(totals.transactions > 0 AND totals.newVisits IS NULL) > 0, 1, 0) AS will_buy_on_return_visit
  FROM `data-to-insights.ecommerce.web_analytics`
  GROUP BY fullvisitorid
)
  SELECT
      CONCAT(fullvisitorid, "-",CAST(visitId AS STRING)) AS unique_session_id,
      # labels
      will_buy_on_return_visit,
      MAX(CAST(h.eCommerceAction.action_type AS INT64)) AS latest_ecommerce_progress,
      # behavior on the site
      IFNULL(totals.bounces, 0) AS bounces,
      IFNULL(totals.timeOnSite, 0) AS time_on_site,
      totals.pageviews,
      # where the visitor came from
      trafficSource.source,
      trafficSource.medium,
      channelGrouping,
      # mobile or desktop
      device.deviceCategory,
      # geographic
      IFNULL(geoNetwork.country, "") AS country
  FROM `data-to-insights.ecommerce.web_analytics`,
     UNNEST(hits) AS h
    JOIN all_visitor_stats USING(fullvisitorid)
  WHERE
    # only predict for new visits
    totals.newVisits = 1
    AND date BETWEEN "20170701" AND "20170801" # test 1 month
  GROUP BY
  unique_session_id,
  will_buy_on_return_visit,
  bounces,
  time_on_site,
  totals.pageviews,
  trafficSource.source,
  trafficSource.medium,
  channelGrouping,
  device.deviceCategory,
  country
)
)
ORDER BY
  predicted_will_buy_on_return_visit DESC;'