Merge pull request #2 from sapiris/master

Modifications for pip

Author: mmaiers-nmdp

grim/conf/minimal-configuration.json

@@ -35,16 +35,18 @@
   "number_of_pop_results": 100,
   "output_MUUG": true,
   "output_haplotypes": true,
-  "node_csv_file": "imputation/graph_generation/output/csv/nodes.csv",
-  "edges_csv_file": "imputation/graph_generation/output/csv/edges.csv",
-  "info_node_csv_file": "imputation/graph_generation/output/csv/info_node.csv",
-  "top_links_csv_file": "imputation/graph_generation/output/csv/top_links.csv",
+  "graph_files_path": "output/csv" ,
+  "node_csv_file": "nodes.csv",
+  "edges_csv_file": "edges.csv",
+  "info_node_csv_file": "info_node.csv",
+  "top_links_csv_file": "top_links.csv",
   "imputation_in_file": "validation/simulation/data/simulated_donor.csv",
   "imputation_out_umug_freq_filename": "don.umug.freqs",
   "imputation_out_umug_pops_filename": "don.umug.pops",
   "imputation_out_hap_freq_filename": "don.hap.freqs",
   "imputation_out_hap_pops_filename": "don.hap.pops",
   "imputation_out_miss_filename": "don.miss",
   "imputation_out_problem_filename": "don.problem",
-  "max_haplotypes_number_in_phase": 100
+  "max_haplotypes_number_in_phase": 100,
+  "imuptation_out_path": "output"
 }

grim/grim.py

@@ -23,18 +23,28 @@
 #
 
 
-from validation import runfile
-from imputation.graph_generation import generate_neo4j_multi_hpf
+from .validation import runfile
+from .imputation.graph_generation import generate_neo4j_multi_hpf
 
-from imputation.imputegl import Imputation
-from imputation.imputegl.networkx_graph import Graph
+from .imputation.imputegl import Imputation
+from .imputation.imputegl.networkx_graph import Graph
+import os
 
-def graph_freqs(conf_file = "./conf/minimal-configuration.json", for_em = False,  em_pop=None, freq_file='hpf.csv', path='imputation/graph_generation/' ):
-    generate_neo4j_multi_hpf.generate_graph(freq_file=freq_file, path=path, config_file=conf_file, em_pop=em_pop,
+def graph_freqs(conf_file = "",  for_em = False,  em_pop=None ):
+    if conf_file == "":
+        conf_file = os.path.dirname(os.path.realpath(__file__))  + '/conf/minimal-configuration.json'
+
+
+    generate_neo4j_multi_hpf.generate_graph(config_file=conf_file,  em_pop=em_pop,
                        em=for_em)
 
-def impute(conf_file = "./conf/minimal-configuration.json"):
-    runfile.run_impute(conf_file)
+def impute(conf_file = ""):
+    project_dir_in_file, project_dir_graph = "", ""
+    if conf_file == "":
+        conf_file = os.path.dirname(os.path.realpath(__file__)) + '/conf/minimal-configuration.json'
+        project_dir_graph =  os.path.dirname(os.path.realpath(__file__)) + '/imputation/graph_generation/'
+        project_dir_in_file =  os.path.dirname(os.path.realpath(__file__)) + '/'
+    runfile.run_impute(conf_file, project_dir_graph, project_dir_in_file)
 
 def impute_instance(config):
     graph = Graph(config)

grim/imputation/graph_generation/generate_neo4j_multi_hpf.py

@@ -192,16 +192,17 @@ def loci_order(loc_values):
 
     return FULL_LOCI, full_name_index_dict
 
-def generate_graph(freq_file = 'hpf.csv', path = '', config_file = "../../conf/minimal-configuration.json", em_pop = None, em= False):
+def generate_graph(config_file = "../../conf/minimal-configuration.json", em_pop = None, em= False):
     ##############################################################################
     # Configure
     ##############################################################################
     # set output directory and create it if it doesn't exist
-    csvdir = path +"output/csv"
+    csvdir = "output/csv"
     pathlib.Path(csvdir).mkdir(parents=True, exist_ok=True)
 
+
     # Input file
-    freq_file = path + 'output/' + freq_file
+    #freq_file = path  + freq_file
 
     parser = argparse.ArgumentParser()
     parser.add_argument("-c", "--config",
@@ -222,6 +223,9 @@ def generate_graph(freq_file = 'hpf.csv', path = '', config_file = "../../conf/m
         pops = em_pop
     freq_trim = conf.get("freq_trim_threshold")
 
+    freq_file =  conf.get("freq_file", "default" )
+    if freq_file == "default":
+        freq_file = os.path.dirname(os.path.realpath(__file__)) +  '/output/hpf.csv'
     dict_count_of_pop = {}
     #if em:
     for pop in pops:

grim/validation/runfile.py

@@ -7,24 +7,31 @@
 
 sys.path.insert(0, os.path.join(".."))
 
-from imputation.imputegl import Imputation
-from imputation.imputegl.networkx_graph import Graph
+from ..imputation.imputegl import Imputation
+from ..imputation.imputegl.networkx_graph import Graph
 
 # Profiler start
 #pr = cProfile.Profile()
 #pr.enable()
 
-def run_impute(conf_file = "../conf/minimal-configuration.json"):
+def run_impute(conf_file = "../conf/minimal-configuration.json", project_dir_graph = "", project_dir_in_file = ""):
 
     configuration_file = conf_file
 
-    project_dir = ""# "../"
-    output_dir = "output/"
+    #project_dir = ""# "../"
+    #output_dir = "output/"
+
 
     # Read configuration file and load properties
     with open(configuration_file) as f:
         json_conf = json.load(f)
 
+    graph_files_path = json_conf.get("graph_files_path")
+    if graph_files_path[-1] != '/':
+        graph_files_path += '/'
+    output_dir = json_conf.get("imuptation_out_path", "output")
+    if output_dir[-1] != '/':
+        output_dir += '/'
     config = {
         "planb": json_conf.get('planb', True),
         "pops": json_conf.get('populations'),
@@ -34,10 +41,10 @@ def run_impute(conf_file = "../conf/minimal-configuration.json"):
         "number_of_pop_results": json_conf.get('number_of_pop_results', 100),
         "output_MUUG": json_conf.get("output_MUUG", True),
         "output_haplotypes": json_conf.get("output_haplotypes", False),
-        "node_file": project_dir + json_conf.get("node_csv_file"),
-        "top_links_file": project_dir + json_conf.get("top_links_csv_file"),
-        "edges_file": project_dir + json_conf.get("edges_csv_file"),
-        "imputation_input_file": project_dir+  json_conf.get("imputation_in_file"),
+        "node_file": project_dir_graph + graph_files_path + json_conf.get("node_csv_file"),
+        "top_links_file": project_dir_graph + graph_files_path + json_conf.get("top_links_csv_file"),
+        "edges_file": project_dir_graph + graph_files_path +json_conf.get("edges_csv_file"),
+        "imputation_input_file": project_dir_in_file + json_conf.get("imputation_in_file"),
         "imputation_out_umug_freq_file": output_dir + json_conf.get("imputation_out_umug_freq_filename"),
         "imputation_out_umug_pops_file": output_dir + json_conf.get("imputation_out_umug_pops_filename"),
         "imputation_out_hap_freq_file": output_dir + json_conf.get("imputation_out_hap_freq_filename"),
@@ -54,11 +61,11 @@ def run_impute(conf_file = "../conf/minimal-configuration.json"):
                     [[1], [2, 3], [4], [5]],
                     [[1], [2], [3], [4], [5]]
                 ]),
-        "pops_count_file": project_dir + json_conf.get("pops_count_file",'' ),
+        "pops_count_file": project_dir_graph + json_conf.get("pops_count_file",'' ),
         "use_pops_count_file": json_conf.get("pops_count_file",False),
         "number_of_options_threshold": json_conf.get("number_of_options_threshold", 100000),
         "max_haplotypes_number_in_phase": json_conf.get("max_haplotypes_number_in_phase",100 ),
-        "bin_imputation_input_file": project_dir + json_conf.get("bin_imputation_in_file", "None"),
+        "bin_imputation_input_file": project_dir_in_file + json_conf.get("bin_imputation_in_file", "None"),
         "nodes_for_plan_A": json_conf.get("Plan_A_Matrix", []),
         "save_mode": json_conf.get("save_space_mode", False)
 

requirements.txt

@@ -1,2 +1,2 @@
-numpy==1.20.2
+numpy>=1.20.2
 networkx==2.5.1