Merge pull request #1 from NICD-UK/script-templates

Script templates

README.md

@@ -9,7 +9,7 @@ pip install cookiecutter
 cookiecutter https://github.com/NICD-UK/project-template
 ```
 
-You will be prompted for nine inputs:
+You will be prompted for eleven inputs:
 
 1. Project Name
 2. Project Directory Name
@@ -19,8 +19,9 @@ You will be prompted for nine inputs:
 6. Project Sponsor Email
 7. Project Summary
 8. Raw Data Directory
-9. `venv` Project (No / Yes)
-10. `git` Project (No / Yes)
+9. Language (Python / R)
+10. `venv` Project (No / Yes)
+11. `git` Project (No / Yes)
 
 ## Organization
 
@@ -32,7 +33,6 @@ data/
 ├─ model/
 ├─ raw/
 ├─ wrangle/
-notebooks/
 reports/
 ├─ clean/
 ├─ final/
@@ -50,7 +50,7 @@ src/
 - **Determine Objectives:**
 - **Determine Deliverables:**
 - **Determine Resources:**
-- **Plan Project:**
+- **Plan Project:** 
 
 ### 2. Data Preparation and Understanding
 
@@ -60,16 +60,16 @@ src/
 
 ### 3. Prototyping
 
-- **Develop Data Product**
-- **Evaluate Data Product**
-- **Approve Data Product**
+- **Develop Data Product:**
+- **Evaluate Data Product:**
+- **Approve Data Product:**
 
 ### 4. Production
 
-- **Deploy Data Product**
-- **Monitor Data Product**
-- **Maintain Data Product**
-- **Close Project**
+- **Deploy Data Product:**
+- **Monitor Data Product:**
+- **Maintain Data Product:**
+- **Close Project:**
 
 ## Guide
 

cookiecutter.json

@@ -7,6 +7,7 @@
     "project_sponsor_email": "Project Sponsor Email",
     "project_summary": "Project Summary",
     "raw_data_directory": "data/raw",
+    "language": ["Python", "R"],
     "venv_project": ["No", "Yes"],
     "git_project": ["No", "Yes"]
 }

hooks/post_gen_project.py

@@ -1,7 +1,21 @@
 import subprocess
+import glob
+import os
 
 venv_project = "{{cookiecutter.venv_project}}"
 git_project = "{{cookiecutter.git_project}}"
+language = "{{cookiecutter.language}}"
+
+# create Python project
+if language == "Python":
+    os.remove("{{cookiecutter.project_directory_name}}.Rproj")
+    for file in glob.glob("**/*.Rmd", recursive=True):
+        os.remove(file)
+
+# create R project
+if language == "R":
+    for file in glob.glob("**/*.py", recursive=True):
+        os.remove(file)
 
 # create venv project
 if venv_project == "Yes":   

{{cookiecutter.project_directory_name}}/reports/clean/clean.Rmd

@@ -0,0 +1,16 @@
+# Load Libraries
+```{r message=FALSE}
+library(glue)
+library(here)
+library(tidyverse)
+```
+
+# Setup
+```{r}
+data_name <- "<data-name>"
+```
+
+# Read Data
+```{r}
+clean_data <- read_rds(here("data", "clean", glue("{data_name}.rds")))
+```

{{cookiecutter.project_directory_name}}/reports/clean/clean.py

@@ -0,0 +1,10 @@
+#%% Load Libraries
+import pandas
+from pyprojroot import here
+import os
+
+#%% Setup
+data_name = "<data-name>"
+
+#%% Read Data
+clean_data = pandas.read_pickle(os.path.join(here(), "data", "clean", f"{data_name}.pkl"))

{{cookiecutter.project_directory_name}}/reports/wrangle/wrangle.Rmd

@@ -0,0 +1,16 @@
+# Load Libraries
+```{r message=FALSE}
+library(glue)
+library(here)
+library(tidyverse)
+```
+
+# Setup
+```{r}
+data_name <- "<data-name>"
+```
+
+# Read Data
+```{r}
+wrangle_data <- read_rds(here("data", "wrangle", glue("{data_name}.rds")))
+```

{{cookiecutter.project_directory_name}}/reports/wrangle/wrangle.py

@@ -0,0 +1,10 @@
+#%% Load Libraries
+import pandas
+from pyprojroot import here
+import os
+
+#%% Setup
+data_name = "<data-name>"
+
+#%% Read Data
+wrangle_data = pandas.read_pickle(os.path.join(here(), "data", "wrangle", f"{data_name}.pkl"))

{{cookiecutter.project_directory_name}}/src/README.md

@@ -0,0 +1,28 @@
+# Transformation Checklist
+
+## Motivation
+
+## Cleaning Checklist
+
+For each data source:
+
+- [ ] read data from `/data/raw/`
+- [ ] ...
+- [ ] write data to `/data/clean/`
+
+## Wrangling Checklist
+
+For each data product:
+
+- [ ] read data from `/data/clean/`
+- [ ] ...
+- [ ] write data to `/data/wrangle/`
+
+## Processing
+
+For models:
+
+
+
+
+

{{cookiecutter.project_directory_name}}/src/clean/clean.Rmd

@@ -0,0 +1,26 @@
+# Load Libraries
+```{r message=FALSE}
+library(glue)
+library(here)
+library(tidyverse)
+```
+
+# Setup
+```{r}
+data_name <- "<data-name>"
+```
+
+# Read Data
+```{r}
+raw_data <- read_csv(here("data", "raw", glue("{data_name}.csv")))
+```
+
+# Clean Data
+```{r}
+clean_data <- raw_data
+```
+
+# Write Data
+```{r}
+write_rds(clean_data, here("data", "clean", glue("{data_name}.rds")))
+```

{{cookiecutter.project_directory_name}}/src/clean/clean.py

@@ -0,0 +1,16 @@
+#%% Load Libraries
+import pandas
+from pyprojroot import here
+import os
+
+#%% Setup
+data_name = "<data-name>"
+
+#%% Read Data
+raw_data = pandas.read_csv(os.path.join(here(), "data", "raw", f"{data_name}.csv"))
+
+#%% Clean Data
+clean_data = raw_data
+
+#%% Write Data
+clean_data.to_pickle(os.path.join(here(), "data", "clean", f"{data_name}.pkl"))

{{cookiecutter.project_directory_name}}/src/model/model.Rmd

@@ -0,0 +1,16 @@
+# Load Libraries
+```{r message=FALSE}
+library(glue)
+library(here)
+library(tidyverse)
+```
+
+# Setup
+```{r}
+data_name <- "<data-name>"
+```
+
+# Read Data
+```{r}
+wrangle_data <- read_rds(here("data", "wrangle", glue("{data_name}.rds")))
+```

{{cookiecutter.project_directory_name}}/src/model/model.py

@@ -0,0 +1,10 @@
+#%% Load Libraries
+import pandas
+from pyprojroot import here
+import os
+
+#%% Setup
+data_name = "<data-name>"
+
+#%% Read Data
+wrangle_data = pandas.read_pickle(os.path.join(here(), "data", "wrangle", f"{data_name}.pkl"))

{{cookiecutter.project_directory_name}}/src/wrangle/wrangle.Rmd

@@ -0,0 +1,26 @@
+# Load Libraries
+```{r message=FALSE}
+library(glue)
+library(here)
+library(tidyverse)
+```
+
+# Setup
+```{r}
+data_name <- "<data-name>"
+```
+
+# Read Data
+```{r}
+clean_data <- read_rds(here("data", "clean", glue("{data_name}.rds")))
+```
+
+# Wrangle Data
+```{r}
+wrangle_data <- clean_data
+```
+
+# Write Data
+```{r}
+write_rds(wrangle_data, here("data", "wrangle", glue("{data_name}.rds")))
+```

{{cookiecutter.project_directory_name}}/src/wrangle/wrangle.py

@@ -0,0 +1,16 @@
+#%% Load Libraries
+import pandas
+from pyprojroot import here
+import os
+
+#%% Setup
+data_name = "<data-name>"
+
+#%% Read Data
+clean_data = pandas.read_pickle(os.path.join(here(), "data", "clean", f"{data_name}.pkl"))
+
+#%% Clean Data
+wrangle_data = clean_data
+
+#%% Write Data
+wrangle_data.to_pickle(os.path.join(here(), "data", "wrangle", f"{data_name}.pkl"))

{{cookiecutter.project_directory_name}}/{{cookiecutter.project_directory_name}}.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: No
+SaveWorkspace: No
+AlwaysSaveHistory: No
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX