Merge pull request #6 from pvanheus/make_data

Add start of Linux lessons

data/shell/file_list1.csv

@@ -0,0 +1,20 @@
+SRR8364252,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_1.fastq.gz
+SRR8364252,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_2.fastq.gz
+SRR8364253,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_1.fastq.gz
+SRR8364253,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_2.fastq.gz
+SRR8364254,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_1.fastq.gz
+SRR8364254,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_2.fastq.gz
+SRR8364255,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_1.fastq.gz
+SRR8364255,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_2.fastq.gz
+SRR8364256,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_1.fastq.gz
+SRR8364256,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_2.fastq.gz
+SRR8364257,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_1.fastq.gz
+SRR8364257,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_2.fastq.gz
+SRR8364258,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_1.fastq.gz
+SRR8364258,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_2.fastq.gz
+SRR8364259,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_1.fastq.gz
+SRR8364259,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_2.fastq.gz
+SRR8364260,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_1.fastq.gz
+SRR8364260,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_2.fastq.gz
+SRR8364261,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_1.fastq.gz
+SRR8364261,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_2.fastq.gz

data/shell/file_list2.csv

@@ -0,0 +1,20 @@
+SRR8364252,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_2.fastq.gz
+SRR8364252,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364252_2.fastq.gz
+SRR8364253,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_2.fastq.gz
+SRR8364253,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364253_2.fastq.gz
+SRR8364254,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_2.fastq.gz
+SRR8364254,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364254_2.fastq.gz
+SRR8364255,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_2.fastq.gz
+SRR8364255,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364255_2.fastq.gz
+SRR8364256,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_2.fastq.gz
+SRR8364256,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364256_2.fastq.gz
+SRR8364257,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_2.fastq.gz
+SRR8364257,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364257_2.fastq.gz
+SRR8364258,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_2.fastq.gz
+SRR8364258,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364258_2.fastq.gz
+SRR8364259,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_2.fastq.gz
+SRR8364259,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364259_2.fastq.gz
+SRR8364260,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_2.fastq.gz
+SRR8364260,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364260_2.fastq.gz
+SRR8364261,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_2.fastq.gz
+SRR8364261,https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_1.fastq.gz;https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads/SRR8364261_2.fastq.gz

data/shell/make_case_data.py

@@ -0,0 +1,52 @@
+#/usr/bin/env python3
+
+from datetime import date
+from random import random
+
+# departments is a list of the Departments of Haiti
+departments = ["Artibonite", "Centre", "Grande'Anse", "Nippes", "Nord", "Nord-Est", "Nord-Ouest", "Sud", "Sud-Est", "Ouest"]
+
+def choose_location():
+    case_by_department = {
+        0.10: "Artibonite",   # 1
+        0.20: "Centre",       # 2
+        0.25: "Grande'Anse",  # 3
+        0.35: "Nippes",       # 4
+        0.45: "Nord",         # 5
+        0.55: "Nord-Est",     # 6
+        0.80: "Ouest",        # 7
+        0.85: "Sud",          # 8
+        0.90: "Sud-Est",      # 9
+        0.95: "Nord-Ouest"    # 10
+    }
+
+    for key in case_by_department:
+        if random() < key:
+            return case_by_department[key]
+
+
+def make_case_data(num_cases=1000, min_date=date(2015, 1, 1), max_date=date(2015, 2, 28)):
+    print("case_id,department,case_date,gender,age,age_unit")
+    for i in range(num_cases):
+        case_id = f'CAS{i+1:05d}'
+        location = choose_location()
+        gender = 'M' if random() < 0.4 else 'F'
+        age_choice = random()
+        if age_choice < 0.2:
+            age = int(random() * 12)
+            age_unit = 'months'
+        elif age_choice < 0.5:
+            age = int(random() * 15) + 1
+            age_unit = 'years'
+        else:
+            age = int(random() * 35) + 16
+            age_unit = 'years'
+        case_date = date.fromordinal(min_date.toordinal() + int(random() * (max_date.toordinal() - min_date.toordinal())))
+        print(f"{case_id},{location},{case_date},{gender},{age},{age_unit}")
+
+if __name__ == '__main__':
+    make_case_data()
+
+
+
+# sample id /lat/ long/iso location code /strain /gender / age 

data/shell/make_file_list1.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+url=https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads
+
+for file in $(ls reads/) ; do 
+    sample=${file%*_[12].fastq.gz}
+    echo $sample,${url}/$file
+done

data/shell/make_file_list2.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+url=https://pathogen-genomics-march-2024.sanbi.ac.za/data/shell/reads
+
+for file in $(ls reads/) ; do
+    sample=${file%*_[12].fastq.gz}
+    echo $sample,${url}/${sample}_1.fastq.gz\;${url}/${sample}_2.fastq.gz
+done