Skip to content

Commit 9aa7a38

Browse files
committed
deploy: 6b31bcc
1 parent 610064e commit 9aa7a38

123 files changed

Lines changed: 1453 additions & 1419 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

assets/vhs/cli-cicd-workflows.gif

-466 KB
Loading

assets/vhs/cli-cicd-workflows.tape

Lines changed: 10 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -8,44 +8,38 @@ Set Width 1200
88
Set Height 700
99
Set Theme "Dracula"
1010

11-
Type "# Production CI/CD Data Validation Workflows"
11+
Type "# Example of a Production CI/CD Data Validation Workflow"
1212
Enter
1313
Sleep 2s
1414

1515
Type ""
1616
Enter
17-
Type "# Pipeline Step 1: Data integrity check with exit codes"
17+
Type "# Pipeline Step 1: Checking for duplicates while using exit codes (this fails)"
1818
Enter
1919
Type "pb validate small_table --check rows-distinct --exit-code"
2020
Enter
21-
Type "echo 'Pipeline result:' \$?"
22-
Enter
23-
Sleep 5s
21+
Sleep 10s
2422

2523
Type ""
2624
Enter
27-
Type "# Pipeline Step 2: Critical columns validation"
25+
Type "# Pipeline Step 2: Checking for null values in an important column (this passes)"
2826
Enter
2927
Type "pb validate small_table --check col-vals-not-null --column date_time --exit-code"
3028
Enter
31-
Type "echo 'Validation status:' \$?"
32-
Enter
33-
Sleep 5s
29+
Sleep 10s
3430

3531
Type ""
3632
Enter
37-
Type "# Pipeline Step 3: Business rules validation"
38-
Enter
39-
Type "pb validate small_table --check col-vals-gt --column a --value 0 --exit-code"
33+
Type "# Pipeline Step 3: Checking for values greater than 2 (this one fails)"
4034
Enter
41-
Type "echo 'Business rule check:' \$?"
35+
Type "pb validate small_table --check col-vals-gt --column a --value 2 --exit-code"
4236
Enter
43-
Sleep 5s
37+
Sleep 10s
4438

4539
Type ""
4640
Enter
47-
Type "# Use in GitHub Actions, GitLab CI, or any automation platform"
41+
Type "# Use in GitHub Actions or any automation platform"
4842
Enter
4943
Type "echo 'Exit codes: 0 = success, 1 = validation failed'"
5044
Enter
51-
Sleep 3s
45+
Sleep 8s
1.1 MB
Loading
Lines changed: 34 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# VHS tape for complete validation workflow
2-
# Shows realistic end-to-end data quality checking
2+
# Shows realistic end-to-end data quality checking with world cities data
33

44
Output cli-complete-workflow.gif
55

@@ -14,46 +14,62 @@ Sleep 2s
1414

1515
Type ""
1616
Enter
17-
Type "# Step 1: Explore your data first"
17+
Type "# Step 0: Get the dimensions of your data first"
1818
Enter
19-
Type "pb preview small_table"
19+
Type "pb info worldcities.csv"
2020
Enter
21-
Sleep 5s
21+
Sleep 4s
2222

2323
Type ""
2424
Enter
25-
Type "# Step 2: Check for basic data integrity"
25+
Type "# Step 1: Quickly preview the dataset"
2626
Enter
27-
Type "pb validate small_table --check rows-distinct"
27+
Type "pb preview worldcities.csv --head 3 --tail 2"
2828
Enter
29-
Sleep 5s
29+
Sleep 6s
3030

3131
Type ""
3232
Enter
33-
Type "# Step 3: Validate critical business columns"
33+
Type "# Step 2: Scan for data quality patterns"
3434
Enter
35-
Type "pb validate small_table --check col-vals-not-null --column a --show-extract"
35+
Type "pb scan worldcities.csv"
3636
Enter
37-
Sleep 6s
37+
Sleep 12s
3838

3939
Type ""
4040
Enter
41-
Type "# Step 4: Check data ranges and constraints"
41+
Type "# Step 3: Check for missing values"
4242
Enter
43-
Type "pb validate small_table --check col-vals-in-set --column f --set 'low,mid,high'"
43+
Type "pb missing worldcities.csv"
4444
Enter
45-
Sleep 5s
45+
Sleep 8s
4646

4747
Type ""
4848
Enter
49-
Type "# Step 5: Comprehensive data profiling"
49+
Type "# Step 4: Validate the population values are provided for each city (i.e., not null)"
5050
Enter
51-
Type "pb scan small_table"
51+
Type "pb validate worldcities.csv --check col-vals-not-null --column population"
5252
Enter
53-
Sleep 6s
53+
Sleep 10s
54+
55+
Type ""
56+
Enter
57+
Type "# Step 5: Check for missing city names (and show problematic rows)"
58+
Enter
59+
Type "pb validate worldcities.csv --check col-vals-not-null --column city_name --show-extract"
60+
Enter
61+
Sleep 10s
5462

5563
Type ""
5664
Enter
57-
Type "echo 'Full data quality pipeline complete!'"
65+
Type "# Step 6: Validate latitude range (latitude: -90 to 90) in two steps"
66+
Enter
67+
Type "pb validate worldcities.csv --check col-vals-ge --column latitude --value -90 --check col-vals-le --column latitude --value 90"
5868
Enter
59-
Sleep 3s
69+
Sleep 10s
70+
71+
Type ""
72+
Enter
73+
Type "echo 'Data quality workflow complete: 41K cities validated!'"
74+
Enter
75+
Sleep 6s
15.7 KB
Loading
Lines changed: 19 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# VHS tape for data exploration and profiling
2-
# Shows preview, missing values, and column summaries
2+
# Shows preview, missing values, and column summaries using real-world city data
33

44
Output cli-data-exploration.gif
55

@@ -8,36 +8,44 @@ Set Width 1200
88
Set Height 800
99
Set Theme "Dracula"
1010

11-
Type "# Data Exploration & Profiling with Pointblank CLI"
11+
Type "# Data Exploration & Profiling with the Pointblank CLI"
1212
Enter
1313
Sleep 2s
1414

1515
Type ""
1616
Enter
17-
Type "# 1. Quick data preview - see structure and sample rows"
17+
Type "# 0. Exploring world cities dataset: get the table dimensions"
1818
Enter
19-
Type "pb preview small_table"
19+
Type "pb info worldcities.csv"
2020
Enter
21-
Sleep 6s
21+
Sleep 4s
2222

2323
Type ""
2424
Enter
25-
Type "# 2. Missing values analysis - identify data gaps"
25+
Type "# 1. Quick data preview: see structure and sample rows"
2626
Enter
27-
Type "pb missing small_table"
27+
Type "pb preview worldcities.csv --head 3 --tail 3"
2828
Enter
29-
Sleep 6s
29+
Sleep 8s
3030

3131
Type ""
3232
Enter
33-
Type "# 3. Comprehensive data scan - statistical overview"
33+
Type "# 2. Missing values analysis: identify data gaps"
3434
Enter
35-
Type "pb scan small_table"
35+
Type "pb missing worldcities.csv"
3636
Enter
3737
Sleep 8s
3838

3939
Type ""
4040
Enter
41-
Type "echo 'Complete data profiling in seconds - no Python required!'"
41+
Type "# 3. Comprehensive data scan: statistical overview"
42+
Enter
43+
Type "pb scan worldcities.csv"
44+
Enter
45+
Sleep 10s
46+
47+
Type ""
48+
Enter
49+
Type "echo 'Complete data profiling in seconds with the Pointblank CLI'"
4250
Enter
4351
Sleep 3s
385 KB
Loading

assets/vhs/cli-essential-validations.tape

Lines changed: 18 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -10,34 +10,42 @@ Set Theme "Dracula"
1010

1111
Type "# Essential Data Validation with Pointblank CLI"
1212
Enter
13-
Sleep 2s
13+
Sleep 4s
1414

1515
Type ""
1616
Enter
17-
Type "# 1. Check for duplicate rows (most common data quality issue)"
17+
Type "# 0. Get the table dimensions, just to know what you're working with"
1818
Enter
19-
Type "pb validate small_table --check rows-distinct"
19+
Type "pb info small_table"
2020
Enter
21-
Sleep 6s
21+
Sleep 8s
2222

2323
Type ""
2424
Enter
25-
Type "# 2. Find missing values in critical columns"
25+
Type "# 1. Check for duplicate rows (the most common data quality issue)"
2626
Enter
27-
Type "pb validate small_table --check col-vals-not-null --column a"
27+
Type "pb validate small_table --check rows-distinct"
2828
Enter
29-
Sleep 6s
29+
Sleep 8s
3030

3131
Type ""
3232
Enter
33-
Type "# 3. When validation fails, see exactly which rows are problematic"
33+
Type "# 2. Find missing values in important columns"
3434
Enter
35-
Type "pb validate small_table --check col-vals-not-null --column b --show-extract"
35+
Type "pb validate small_table --check col-vals-not-null --column c"
3636
Enter
3737
Sleep 8s
3838

39+
Type ""
40+
Enter
41+
Type "# 3. When validation fails, see exactly which rows are problematic with --show-extract"
42+
Enter
43+
Type "pb validate small_table --check col-vals-not-null --column c --show-extract"
44+
Enter
45+
Sleep 10s
46+
3947
Type ""
4048
Enter
4149
Type "echo 'Essential validations: duplicates, nulls, with data extracts'"
4250
Enter
43-
Sleep 3s
51+
Sleep 6s

assets/vhs/cli-getting-started.gif

585 KB
Loading

assets/vhs/cli-getting-started.tape

Lines changed: 17 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -8,36 +8,44 @@ Set Width 1200
88
Set Height 700
99
Set Theme "Dracula"
1010

11-
Type "# Getting Started with Pointblank CLI"
11+
Type "# Getting Started with the Pointblank CLI"
1212
Enter
13-
Sleep 2s
13+
Sleep 5s
1414

1515
Type ""
1616
Enter
1717
Type "# See all available commands"
1818
Enter
1919
Type "pb --help"
2020
Enter
21-
Sleep 6s
21+
Sleep 10s
22+
23+
Type ""
24+
Enter
25+
Type "# There's a number of datasets you can use for testing"
26+
Enter
27+
Type "pb datasets"
28+
Enter
29+
Sleep 8s
2230

2331
Type ""
2432
Enter
25-
Type "# Quick validation options overview"
33+
Type "# Learn about all the `pb validate` options"
2634
Enter
2735
Type "pb validate --help"
2836
Enter
29-
Sleep 6s
37+
Sleep 12s
3038

3139
Type ""
3240
Enter
33-
Type "# Your first validation - check for duplicates"
41+
Type "# Your first validation: check for duplicates with rows-distinct"
3442
Enter
3543
Type "pb validate small_table --check rows-distinct"
3644
Enter
37-
Sleep 5s
45+
Sleep 10s
3846

3947
Type ""
4048
Enter
41-
Type "echo 'Ready to validate any dataset - CSV, Parquet, or database!'"
49+
Type "# You are now ready to validate any dataset you like: CSV, Parquet, or a DB table"
4250
Enter
43-
Sleep 3s
51+
Sleep 5s

0 commit comments

Comments
 (0)