add code Snippet in documentation (on perf testing)

doc/source/index.rst

@@ -97,6 +97,61 @@ The raiss package outputs imputed GWAS files in the tabular format:
 | rs111876722 |  201922  |      C     |      T     |  0.297  |	0.16 |  5.412   |
 +-------------+----------+------------+------------+---------+-------+----------+
 
+Optimizing RAISS parameter for your data
+========================================
+
+Raiss package contains a function (raiss.imputation_R2.grid_search)
+to assess its performance on your data and fine tune RAISS parameter.
+
+Test procedure :
+1. Mask N SNPs on a chromosome
+2. Imputed masked file
+3. Compute correlation between genotype Z-values to imputed Z-values
+
+To perform this test follow this procedure :
+
+1. Create a folder to store masked z-score files
+2. Create a folder to store z-score files imputed with different parameter
+3. Adapt the following code snippet to apply the function to your data:
+
+.. code-block::
+  :linenos:
+
+  perf_results = raiss.imputation_R2.grid_search(
+      ${path_z-scores_folder},
+      ${path_to_masked_z-scores_folder},
+      ${path_to_imputed_z-scores_folder},
+      ${path_to_reference_panel_folder},
+      ${path_to_LD_matrices_folder},
+      "GWAS_TAG", chrom="chr22",
+      eigen_ratio_grid = [ 1, 0.5 ,0.1, 0.01], # Enter the value you want to test in this list
+      window_size= 500000, buffer_size=125000, l2_regularization=0.1,
+       R2_threshold=0.6)
+  fout = "./Perf_"+GWAS_TAG+".csv"
+  print(perf_results)
+  perf_results.to_csv(fout, sep="\t")
+
+The file Perf_GWAS_TAG ressemble the following output:
+
++----+----+--------------------+-----------------+
+|    |cor |mean_absolute_error |fraction_imputed |
++====+====+====================+=================+
+|1.0 |0.95|       0.243        |      1.0        |
++----+----+--------------------+-----------------+
+| 0.5|0.94|       0.246        |      0.95       |
++----+----+--------------------+-----------------+
+
+The row names correspond to the eigen ratio parameter that was tested.
+The second column is the correlation between imputed and genotyped Z-scores.
+The third column is the mean L1-error between imputed and genotyped Z-scores.
+The fourth column is the fraction of SNPs on the 5000 that were imputed.
+
+The optimal eigen_ratio can vary depending on the density of your reference panel and input data.
+Hence, we recommend to run a grid search to pick the best parameter for your data.
+However, empirically, we never observed a difference of performance from one chromosome to another.
+We suggest testing on the chr22 for computational efficiency.
+
+
 Command Line Usage
 ==================
 

raiss/imputation_R2.py

@@ -24,14 +24,13 @@ def generated_test_data(zscore, N_to_mask=5000, condition=None,  stratifying_vec
     """
     try:
         if isinstance(condition, pd.Series)==True:
+            print("Condition vector")
             masked = np.random.choice(zscore.index[condition], N_to_mask, replace=False)
         else:
-            print("Stratifying vector?")
-            inter_id = zscore.index.intersection(stratifying_vector.index).drop_duplicates(keep='first')
-            print(inter_id[1:10])
-            stratifying_vector = stratifying_vector.loc[inter_id]
-
             if isinstance(stratifying_vector, pd.Series)==True:
+                print("Stratifying vector")
+                inter_id = zscore.index.intersection(stratifying_vector.index).drop_duplicates(keep='first')
+                stratifying_vector = stratifying_vector.loc[inter_id]
                 masked = []
                 binned = np.digitize(stratifying_vector, stratifying_bins)
                 N_bins = len(stratifying_bins)-1

raiss/stat_models.py

@@ -104,6 +104,6 @@ def raiss_model(zt, sig_t, sig_i_t, lamb=0.01, rcond=0.01,  batch=True):
         var_norm = var_in_boundaries(var, lamb)
 
         R2 = ((1+lamb)-var_norm)
-        print(R2)
+
         mu = mu / np.sqrt(R2)
         return({"var" : var, "mu" : mu, "ld_score" : ld_score, "condition_number" : condition_number, "correct_inversion":correct_inversion })