Integrate correlation API

- add new api for gn2-gn3 sample r integration
- delete map for sample list to values
- add db util file
- add python msql-client dependency
- add db for fetching lit correlation results
- add unittests for db utils
- add tests for db_utils
- modify api for fetching lit correlation results
- refactor Mock Database Connector and unittests
- add sql url parser
- add SQL URI env variable
- refactor code for db utils
- modify return data for lit correlation
- refactor tissue correlation endpoint
- replace db_instance with conn

1 files changed, 30 insertions, 9 deletions

diff --git a/gn3/api/correlation.py b/gn3/api/correlation.py
index 53ea6a7..2339088 100644
--- a/gn3/api/correlation.py
+++ b/gn3/api/correlation.py
@@ -1,6 +1,4 @@
 """Endpoints for running correlations"""
-from unittest import mock
-
 from flask import jsonify
 from flask import Blueprint
 from flask import request
@@ -8,11 +6,31 @@ from flask import request
 from gn3.computations.correlations import compute_all_sample_correlation
 from gn3.computations.correlations import compute_all_lit_correlation
 from gn3.computations.correlations import compute_all_tissue_correlation
-
+from gn3.computations.correlations import map_shared_keys_to_values
+from gn3.db_utils import database_connector
 
 correlation = Blueprint("correlation", __name__)
 
 
+@correlation.route("/sample_x/<string:corr_method>", methods=["POST"])
+def compute_sample_integration(corr_method="pearson"):
+    """temporary api to  help integrate genenetwork2  to genenetwork3 """
+
+    correlation_input = request.get_json()
+
+    target_samplelist = correlation_input.get("target_samplelist")
+    target_data_values = correlation_input.get("target_dataset")
+    this_trait_data = correlation_input.get("trait_data")
+
+    results = map_shared_keys_to_values(target_samplelist, target_data_values)
+
+    correlation_results = compute_all_sample_correlation(corr_method=corr_method,
+                                                         this_trait=this_trait_data,
+                                                         target_dataset=results)
+
+    return jsonify(correlation_results)
+
+
 @correlation.route("/sample_r/<string:corr_method>", methods=["POST"])
 def compute_sample_r(corr_method="pearson"):
     """correlation endpoint for computing sample r correlations\
@@ -22,11 +40,11 @@ def compute_sample_r(corr_method="pearson"):
 
     # xtodo move code below to compute_all_sampl correlation
     this_trait_data = correlation_input.get("this_trait")
-    target_datasets = correlation_input.get("target_dataset")
+    target_dataset_data = correlation_input.get("target_dataset")
 
     correlation_results = compute_all_sample_correlation(corr_method=corr_method,
                                                          this_trait=this_trait_data,
-                                                         target_dataset=target_datasets)
+                                                         target_dataset=target_dataset_data)
 
     return jsonify({
         "corr_results": correlation_results
@@ -39,13 +57,16 @@ def compute_lit_corr(species=None, gene_id=None):
     are fetched from the database this is the only case where the db\
     might be needed for actual computing of the correlation results"""
 
-    database_instance = mock.Mock()
+    conn, _cursor_object = database_connector()
     target_traits_gene_ids = request.get_json()
+    target_trait_gene_list = list(target_traits_gene_ids.items())
 
     lit_corr_results = compute_all_lit_correlation(
-        database_instance=database_instance, trait_lists=target_traits_gene_ids,
+        conn=conn, trait_lists=target_trait_gene_list,
         species=species, gene_id=gene_id)
 
+    conn.close()
+
     return jsonify(lit_corr_results)
 
 
@@ -54,10 +75,10 @@ def compute_tissue_corr(corr_method="pearson"):
     """api endpoint fr doing tissue correlation"""
     tissue_input_data = request.get_json()
     primary_tissue_dict = tissue_input_data["primary_tissue"]
-    target_tissues_dict_list = tissue_input_data["target_tissues"]
+    target_tissues_dict = tissue_input_data["target_tissues_dict"]
 
     results = compute_all_tissue_correlation(primary_tissue_dict=primary_tissue_dict,
-                                             target_tissues_dict_list=target_tissues_dict_list,
+                                             target_tissues_data=target_tissues_dict,
                                              corr_method=corr_method)
 
     return jsonify(results)