Add reticulate slides

slides/slides.qmd

@@ -18,7 +18,7 @@ format:
     history: true
     link-external-newwindow: true
 jupyter: python3
-exectute:
+execute:
     echo: true
 ---
 
@@ -123,7 +123,7 @@ tools = importr('tools', robject_translations = d)
 # Pitfalls when using Python and R
 **Integers**
 
-```r 
+```{r} 
 library(reticulate)
 bi <- reticulate::import_builtins()
 
@@ -144,7 +144,8 @@ bi$list(bi$range(0L, 5L))
   - `rpy2.rinterface`, the low-level interface
   - `rpy2.robjects`, the high-level interface
 
-```python
+```{python}
+#| echo: true
 import rpy2
 import rpy2.robjects as robjects
 
@@ -156,29 +157,34 @@ rsum(vector)
 
 # Rpy2: basics
 
-```python
+```{python}
+#| echo: true
 str_vector = robjects.StrVector(['abc', 'def', 'ghi'])
 flt_vector = robjects.FloatVector([0.3, 0.8, 0.7])
 int_vector = robjects.IntVector([1, 2, 3])
 mtx = robjects.r.matrix(robjects.IntVector(range(10)), nrow=5)
+print(mtx)
 ```
 
 # Rpy2: numpy
 
-```python
+```{python}
+#| echo: true
 import numpy as np
 
 from rpy2.robjects import numpy2ri
 from rpy2.robjects import default_converter
 
-rd_m = np.random.random((10, 7))
+rd_m = np.random.random((5, 4))
 
 with (default_converter + numpy2ri.converter).context():
-    mtx2 = robjects.r.matrix(rd_m, nrow = 10)
+    mtx = robjects.r.matrix(rd_m, nrow = 5)
+    print(mtx)
 ```
 
 # Rpy2: pandas
-```python
+```{python}
+#| echo: true
 import pandas as pd
 
 from rpy2.robjects import pandas2ri
@@ -188,11 +194,13 @@ pd_df = pd.DataFrame({'int_values': [1,2,3],
 
 with (default_converter + pandas2ri.converter).context():
     pd_df_r = robjects.DataFrame(pd_df)
+    print(pd_df_r)
 ```
 
 # Rpy2: sparse matrices
 
-```python
+```{python}
+#| echo: true
 import scipy as sp
 
 from anndata2ri import scipy2ri
@@ -201,6 +209,7 @@ sparse_matrix = sp.sparse.csc_matrix(rd_m)
 
 with (default_converter + scipy2ri.converter).context():
     sp_r = scipy2ri.py2rpy(sparse_matrix)
+    print(sp_r)
 ```
 
 # Rpy2: anndata
@@ -233,6 +242,102 @@ with anndata2ri.converter.context():
 
 # Reticulate
 
+![](images/reticulate_table.png)
+
+# Reticulate
+
+```r
+library(reticulate)
+
+bi <- reticulate::import_builtins()
+rd <- reticulate::import("random")
+
+example <- c(1,2,3)
+bi$max(example)
+# [1] 3
+rd$choice(example)
+# [1] 2
+cat(bi$list(bi$reversed(example)))
+# [1] 3 2 1
+```
+
+# Reticulate numpy
+
+```r
+np <- reticulate::import("numpy")
+
+a <- np$asarray(tuple(list(1,2), list(3, 4)))
+b <- np$asarray(list(5,6))
+b <- np$reshape(b, newshape = tuple(1L,2L))
+
+np$concatenate(tuple(a, b), axis=0L)
+#      [,1] [,2]
+# [1,]    1    2
+# [2,]    3    4
+# [3,]    5    6
+```
+
+# Reticulate conversion
+
+```r
+np <- reticulate::import("numpy", convert = FALSE)
+
+a <- np$asarray(tuple(list(1,2), list(3, 4)))
+b <- np$asarray(list(5,6))
+b <- np$reshape(b, newshape = tuple(1L,2L))
+
+np$concatenate(tuple(a, b), axis=0L)
+# array([[1., 2.],
+#        [3., 4.],
+#        [5., 6.]])
+```
+
+You can explicitly convert data types:
+```r
+result <- np$concatenate(tuple(a, b), axis=0L)
+
+py_to_r(result)
+#      [,1] [,2]
+# [1,]    1    2
+# [2,]    3    4
+# [3,]    5    6
+
+result_r <- py_to_r(result)
+r_to_py(result_r)
+# array([[1., 2.],
+#        [3., 4.],
+#        [5., 6.]])
+```
+
+# Reticulate scanpy
+
+```r
+library(anndata)
+library(reticulate)
+sc <- import("scanpy")
+
+adata_path <- "../usecase/data/sc_counts_subset.h5ad"
+adata <- anndata::read_h5ad(adata_path)
+```
+
+We can preprocess & analyse the data:
+```r
+sc$pp$filter_cells(adata, min_genes = 200)
+sc$pp$filter_genes(adata, min_cells = 3)
+sc$pp$pca(adata)
+sc$pp$neighbors(adata)
+sc$tl$umap(adata)
+
+adata
+# AnnData object with n_obs × n_vars = 32727 × 20542
+#     obs: 'dose_uM', 'timepoint_hr', 'well', 'row', 'col', 'plate_name', 'cell_id', 'cell_type', 'split', 'donor_id', 'sm_name', 'control', 'SMILES', 'sm_lincs_id', 'library_id', 'leiden_res1', 'group', 'cell_type_orig', 'plate_well_celltype_reannotated', 'cell_count_by_well_celltype', 'cell_count_by_plate_well', 'n_genes'
+#     var: 'highly_variable', 'means', 'dispersions', 'dispersions_norm', 'n_cells'
+#     uns: 'cell_type_colors', 'celltypist_celltype_colors', 'donor_id_colors', 'hvg', 'leiden_res1_colors', 'log1p', 'neighbors', 'over_clustering', 'rank_genes_groups', 'pca', 'umap'
+#     obsm: 'HTO_clr', 'X_pca', 'X_umap', 'protein_counts'
+#     varm: 'PCs'
+#     obsp: 'connectivities', 'distances'
+```
+
 # Disk-based interoperability
 
 ## General single cell file formats of interest for Python and R