teradataml 20.0.0.1__py3-none-any.whl → 20.0.0.3__py3-none-any.whl

teradataml/data/medical_readings.csv

@@ -0,0 +1,101 @@
+patient_id,record_timestamp,glucose,blood_pressure,insulin,diabetes_pedigree_function,outcome
+0,2024-04-10 11:10:59,148,72,0,0.627,1
+1,2024-04-10 11:10:59,85,66,0,0.351,0
+2,2024-04-10 11:10:59,183,64,0,0.672,1
+3,2024-04-10 11:10:59,89,66,94,0.167,0
+4,2024-04-10 11:10:59,137,40,168,2.288,1
+5,2024-04-10 11:10:59,116,74,0,0.201,0
+6,2024-04-10 11:10:59,78,50,88,0.248,1
+7,2024-04-10 11:10:59,115,0,0,0.134,0
+8,2024-04-10 11:10:59,197,70,543,0.158,1
+9,2024-04-10 11:10:59,125,96,0,0.232,1
+10,2024-04-10 11:10:59,110,92,0,0.191,0
+11,2024-04-10 11:10:59,168,74,0,0.537,1
+12,2024-04-10 11:10:59,139,80,0,1.441,0
+13,2024-04-10 11:10:59,189,60,846,0.398,1
+14,2024-04-10 11:10:59,166,72,175,0.587,1
+15,2024-04-10 11:10:59,100,0,0,0.484,1
+16,2024-04-10 11:10:59,118,84,230,0.551,1
+17,2024-04-10 11:10:59,107,74,0,0.254,1
+18,2024-04-10 11:10:59,103,30,83,0.183,0
+19,2024-04-10 11:10:59,115,70,96,0.529,1
+20,2024-04-10 11:10:59,126,88,235,0.704,0
+21,2024-04-10 11:10:59,99,84,0,0.388,0
+22,2024-04-10 11:10:59,196,90,0,0.451,1
+23,2024-04-10 11:10:59,119,80,0,0.263,1
+24,2024-04-10 11:10:59,143,94,146,0.254,1
+25,2024-04-10 11:10:59,125,70,115,0.205,1
+26,2024-04-10 11:10:59,147,76,0,0.257,1
+27,2024-04-10 11:10:59,97,66,140,0.487,0
+28,2024-04-10 11:10:59,145,82,110,0.245,0
+29,2024-04-10 11:10:59,117,92,0,0.337,0
+30,2024-04-10 11:10:59,109,75,0,0.546,0
+31,2024-04-10 11:10:59,158,76,245,0.851,1
+32,2024-04-10 11:10:59,88,58,54,0.267,0
+33,2024-04-10 11:10:59,92,92,0,0.188,0
+34,2024-04-10 11:10:59,122,78,0,0.512,0
+35,2024-04-10 11:10:59,103,60,192,0.966,0
+36,2024-04-10 11:10:59,138,76,0,0.42,0
+37,2024-04-10 11:10:59,102,76,0,0.665,1
+38,2024-04-10 11:10:59,90,68,0,0.503,1
+39,2024-04-10 11:10:59,111,72,207,1.39,1
+40,2024-04-10 11:10:59,180,64,70,0.271,0
+41,2024-04-10 11:10:59,133,84,0,0.696,0
+42,2024-04-10 11:10:59,106,92,0,0.235,0
+43,2024-04-10 11:10:59,171,110,240,0.721,1
+44,2024-04-10 11:10:59,159,64,0,0.294,0
+45,2024-04-10 11:10:59,180,66,0,1.893,1
+46,2024-04-10 11:10:59,146,56,0,0.564,0
+47,2024-04-10 11:10:59,71,70,0,0.586,0
+48,2024-04-10 11:10:59,103,66,0,0.344,1
+49,2024-04-10 11:10:59,105,0,0,0.305,0
+50,2024-04-10 11:10:59,103,80,82,0.491,0
+51,2024-04-10 11:10:59,101,50,36,0.526,0
+52,2024-04-10 11:10:59,88,66,23,0.342,0
+53,2024-04-10 11:10:59,176,90,300,0.467,1
+54,2024-04-10 11:10:59,150,66,342,0.718,0
+55,2024-04-10 11:10:59,73,50,0,0.248,0
+56,2024-04-10 11:10:59,187,68,304,0.254,1
+57,2024-04-10 11:10:59,100,88,110,0.962,0
+58,2024-04-10 11:10:59,146,82,0,1.781,0
+59,2024-04-10 11:10:59,105,64,142,0.173,0
+60,2024-04-10 11:10:59,84,0,0,0.304,0
+61,2024-04-10 11:10:59,133,72,0,0.27,1
+62,2024-04-10 11:10:59,44,62,0,0.587,0
+63,2024-04-10 11:10:59,141,58,128,0.699,0
+64,2024-04-10 11:10:59,114,66,0,0.258,1
+65,2024-04-10 11:10:59,99,74,0,0.203,0
+66,2024-04-10 11:10:59,109,88,0,0.855,1
+67,2024-04-10 11:10:59,109,92,0,0.845,0
+68,2024-04-10 11:10:59,95,66,38,0.334,0
+69,2024-04-10 11:10:59,146,85,100,0.189,0
+70,2024-04-10 11:10:59,100,66,90,0.867,1
+71,2024-04-10 11:10:59,139,64,140,0.411,0
+72,2024-04-10 11:10:59,126,90,0,0.583,1
+73,2024-04-10 11:10:59,129,86,270,0.231,0
+74,2024-04-10 11:10:59,79,75,0,0.396,0
+75,2024-04-10 11:10:59,0,48,0,0.14,0
+76,2024-04-10 11:10:59,62,78,0,0.391,0
+77,2024-04-10 11:10:59,95,72,0,0.37,0
+78,2024-04-10 11:10:59,131,0,0,0.27,1
+79,2024-04-10 11:10:59,112,66,0,0.307,0
+80,2024-04-10 11:10:59,113,44,0,0.14,0
+81,2024-04-10 11:10:59,74,0,0,0.102,0
+82,2024-04-10 11:10:59,83,78,71,0.767,0
+83,2024-04-10 11:10:59,101,65,0,0.237,0
+84,2024-04-10 11:10:59,137,108,0,0.227,1
+85,2024-04-10 11:10:59,110,74,125,0.698,0
+86,2024-04-10 11:10:59,106,72,0,0.178,0
+87,2024-04-10 11:10:59,100,68,71,0.324,0
+88,2024-04-10 11:10:59,136,70,110,0.153,1
+89,2024-04-10 11:10:59,107,68,0,0.165,0
+90,2024-04-10 11:10:59,80,55,0,0.258,0
+91,2024-04-10 11:10:59,123,80,176,0.443,0
+92,2024-04-10 11:10:59,81,78,48,0.261,0
+93,2024-04-10 11:10:59,134,72,0,0.277,1
+94,2024-04-10 11:10:59,142,82,64,0.761,0
+95,2024-04-10 11:10:59,144,72,228,0.255,0
+96,2024-04-10 11:10:59,92,62,0,0.13,0
+97,2024-04-10 11:10:59,71,48,76,0.323,0
+98,2024-04-10 11:10:59,93,50,64,0.356,0
+99,2024-04-10 11:10:59,122,90,220,0.325,1

teradataml/data/naivebayestextclassifier_example.json

@@ -1,7 +1,7 @@
 {
  
   "token_table" :{
-          "doc_id" : "varchar(30)",
+          "doc_id" : "INTEGER",
           "token" : "varchar(30)",
           "category" : "varchar(30)"
             }

teradataml/data/naivebayestextclassifierpredict_example.json

@@ -17,5 +17,16 @@
     "doc_id" : "integer",
     "text_data" : "varchar(3000)",
     "category" : "varchar(20)"
+  },
+  "complaints_test_tokenized":{
+    "doc_id": "integer",
+    "doc_name": "varchar(30)",
+    "sn": "integer",
+    "token": "varchar(1024) CHARACTER SET UNICODE NOT CASESPECIFIC"
+  },
+  "complaints_tokens_model": {
+    "token": "varchar(100)",
+    "category": "varchar(100)",
+    "prob": "double precision"
   }
 }

teradataml/data/patient_profile.csv

@@ -0,0 +1,101 @@
+patient_id,record_timestamp,pregnancies,age,bmi,skin_thickness
+0,2024-04-10 11:10:59,6,50,33.6,35
+1,2024-04-10 11:10:59,1,31,26.6,29
+2,2024-04-10 11:10:59,8,32,23.3,0
+3,2024-04-10 11:10:59,1,21,28.1,23
+4,2024-04-10 11:10:59,0,33,43.1,35
+5,2024-04-10 11:10:59,5,30,25.6,0
+6,2024-04-10 11:10:59,3,26,31.0,32
+7,2024-04-10 11:10:59,10,29,35.3,0
+8,2024-04-10 11:10:59,2,53,30.5,45
+9,2024-04-10 11:10:59,8,54,0.0,0
+10,2024-04-10 11:10:59,4,30,37.6,0
+11,2024-04-10 11:10:59,10,34,38.0,0
+12,2024-04-10 11:10:59,10,57,27.1,0
+13,2024-04-10 11:10:59,1,59,30.1,23
+14,2024-04-10 11:10:59,5,51,25.8,19
+15,2024-04-10 11:10:59,7,32,30.0,0
+16,2024-04-10 11:10:59,0,31,45.8,47
+17,2024-04-10 11:10:59,7,31,29.6,0
+18,2024-04-10 11:10:59,1,33,43.3,38
+19,2024-04-10 11:10:59,1,32,34.6,30
+20,2024-04-10 11:10:59,3,27,39.3,41
+21,2024-04-10 11:10:59,8,50,35.4,0
+22,2024-04-10 11:10:59,7,41,39.8,0
+23,2024-04-10 11:10:59,9,29,29.0,35
+24,2024-04-10 11:10:59,11,51,36.6,33
+25,2024-04-10 11:10:59,10,41,31.1,26
+26,2024-04-10 11:10:59,7,43,39.4,0
+27,2024-04-10 11:10:59,1,22,23.2,15
+28,2024-04-10 11:10:59,13,57,22.2,19
+29,2024-04-10 11:10:59,5,38,34.1,0
+30,2024-04-10 11:10:59,5,60,36.0,26
+31,2024-04-10 11:10:59,3,28,31.6,36
+32,2024-04-10 11:10:59,3,22,24.8,11
+33,2024-04-10 11:10:59,6,28,19.9,0
+34,2024-04-10 11:10:59,10,45,27.6,31
+35,2024-04-10 11:10:59,4,33,24.0,33
+36,2024-04-10 11:10:59,11,35,33.2,0
+37,2024-04-10 11:10:59,9,46,32.9,37
+38,2024-04-10 11:10:59,2,27,38.2,42
+39,2024-04-10 11:10:59,4,56,37.1,47
+40,2024-04-10 11:10:59,3,26,34.0,25
+41,2024-04-10 11:10:59,7,37,40.2,0
+42,2024-04-10 11:10:59,7,48,22.7,18
+43,2024-04-10 11:10:59,9,54,45.4,24
+44,2024-04-10 11:10:59,7,40,27.4,0
+45,2024-04-10 11:10:59,0,25,42.0,39
+46,2024-04-10 11:10:59,1,29,29.7,0
+47,2024-04-10 11:10:59,2,22,28.0,27
+48,2024-04-10 11:10:59,7,31,39.1,32
+49,2024-04-10 11:10:59,7,24,0.0,0
+50,2024-04-10 11:10:59,1,22,19.4,11
+51,2024-04-10 11:10:59,1,26,24.2,15
+52,2024-04-10 11:10:59,5,30,24.4,21
+53,2024-04-10 11:10:59,8,58,33.7,34
+54,2024-04-10 11:10:59,7,42,34.7,42
+55,2024-04-10 11:10:59,1,21,23.0,10
+56,2024-04-10 11:10:59,7,41,37.7,39
+57,2024-04-10 11:10:59,0,31,46.8,60
+58,2024-04-10 11:10:59,0,44,40.5,0
+59,2024-04-10 11:10:59,0,22,41.5,41
+60,2024-04-10 11:10:59,2,21,0.0,0
+61,2024-04-10 11:10:59,8,39,32.9,0
+62,2024-04-10 11:10:59,5,36,25.0,0
+63,2024-04-10 11:10:59,2,24,25.4,34
+64,2024-04-10 11:10:59,7,42,32.8,0
+65,2024-04-10 11:10:59,5,32,29.0,27
+66,2024-04-10 11:10:59,0,38,32.5,30
+67,2024-04-10 11:10:59,2,54,42.7,0
+68,2024-04-10 11:10:59,1,25,19.6,13
+69,2024-04-10 11:10:59,4,27,28.9,27
+70,2024-04-10 11:10:59,2,28,32.9,20
+71,2024-04-10 11:10:59,5,26,28.6,35
+72,2024-04-10 11:10:59,13,42,43.4,0
+73,2024-04-10 11:10:59,4,23,35.1,20
+74,2024-04-10 11:10:59,1,22,32.0,30
+75,2024-04-10 11:10:59,1,22,24.7,20
+76,2024-04-10 11:10:59,7,41,32.6,0
+77,2024-04-10 11:10:59,5,27,37.7,33
+78,2024-04-10 11:10:59,0,26,43.2,0
+79,2024-04-10 11:10:59,2,24,25.0,22
+80,2024-04-10 11:10:59,3,22,22.4,13
+81,2024-04-10 11:10:59,2,22,0.0,0
+82,2024-04-10 11:10:59,7,36,29.3,26
+83,2024-04-10 11:10:59,0,22,24.6,28
+84,2024-04-10 11:10:59,5,37,48.8,0
+85,2024-04-10 11:10:59,2,27,32.4,29
+86,2024-04-10 11:10:59,13,45,36.6,54
+87,2024-04-10 11:10:59,2,26,38.5,25
+88,2024-04-10 11:10:59,15,43,37.1,32
+89,2024-04-10 11:10:59,1,24,26.5,19
+90,2024-04-10 11:10:59,1,21,19.1,0
+91,2024-04-10 11:10:59,4,34,32.0,15
+92,2024-04-10 11:10:59,7,42,46.7,40
+93,2024-04-10 11:10:59,4,60,23.8,0
+94,2024-04-10 11:10:59,2,21,24.7,18
+95,2024-04-10 11:10:59,6,40,33.9,27
+96,2024-04-10 11:10:59,2,24,31.6,28
+97,2024-04-10 11:10:59,1,22,20.4,18
+98,2024-04-10 11:10:59,6,23,28.7,30
+99,2024-04-10 11:10:59,1,31,49.7,51

teradataml/data/real_values.csv

@@ -0,0 +1,14 @@
+"TD_TIMECODE","id","val"
+2020-01-01 08:00:00,33,1.2e+02
+2020-02-01 08:00:00,33,1.95e+02
+2020-03-01 08:00:00,33,8e+02
+2020-04-01 08:00:00,33,6.6e+01
+2020-05-01 08:00:00,33,1.44e+02
+2020-06-01 08:00:00,33,2.1e+04
+2020-07-01 08:00:00,33,3.2e+02
+2020-08-01 08:00:00,33,1.44e+02
+2020-09-01 08:00:00,33,2.2e+02
+2020-10-01 08:00:00,33,2.1e+02
+2020-11-01 08:00:00,33,1.34e+02
+2020-12-01 08:00:00,33,1.84e+02
+2020-12-02 08:00:00,33,1.98e+02

teradataml/data/sax_example.json

@@ -5,5 +5,13 @@
     "expenditure": "integer",
     "income": "integer",
     "investment": "integer"
+  },
+  "finance_data4":{
+    "id": "integer",
+    "period": "integer",
+    "expenditure": "float",
+    "income": "float",
+    "investment": "float"
+
   }
 }

teradataml/data/scripts/deploy_script.py

@@ -60,7 +60,7 @@ if not len(features):
     sys.exit(0)
 
 X = np.array(features)
-y = np.array(labels)
+y = np.array(labels).ravel()
 
 clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
 clf.fit(X, y)

teradataml/data/scripts/lightgbm/dataset.template

@@ -0,0 +1,157 @@
+import pandas as pd
+import pickle
+import json
+import numpy as np
+import ast
+import sys
+from collections import OrderedDict
+import base64
+from importlib import import_module
+import sys
+
+DELIMITER = "\t"
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+
+is_lake_system = eval(sys.argv[2])
+model_file_prefix = sys.argv[1]
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+
+### Start of data related arguments processing
+data_partition_column_values = []
+data_present = False
+partition_join = ""
+model = None
+
+# Data related arguments information of indices and types.
+data_args_indices_types = OrderedDict()
+
+func_name = <func_name>
+module_name = <module_name>
+class_name = <class_name>
+all_col_names = <all_col_names>
+all_col_types = <types_of_data_cols>
+data_partition_column_indices = <partition_cols_indices>
+data_partition_column_types = [all_col_types[idx] for idx in data_partition_column_indices]
+
+# Data related arguments values - prepare dictionary and populate data later.
+data_args_values = {}
+
+data_args_info_str = <data_args_info_str>
+
+for data_arg in data_args_info_str.split("--"):
+    _arg_name, _indices, _types = data_arg.split("-")
+    _indices = splitter(_indices, convert_to="int")
+    types = [type_ for idx, type_ in enumerate(all_col_types) if idx in _indices]
+
+    data_args_indices_types[_arg_name] = {"indices": _indices, "types": types}
+    data_args_values[_arg_name] = [] # Keeping empty for each data arg name and populate data later.
+
+### End of data related arguments processing
+
+
+### Start of other arguments processing
+params = json.loads('<params>')
+### End of other arguments processing
+
+
+# Read data - columns information is passed as command line argument and stored in
+# data_args_indices_types dictionary. 
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            data_present = True
+            values = line.split(DELIMITER)
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}"\
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+            # Prepare data dictionary containing only arguments related to data.
+            for arg_name in data_args_values:
+                data_indices = data_args_indices_types[arg_name]["indices"]
+                types = data_args_indices_types[arg_name]["types"]
+                cur_row = []
+                for idx, data_idx in enumerate(data_indices):
+                    cur_row.append(convert_to_type(values[data_idx], types[idx]))
+                data_args_values[arg_name].append(cur_row)
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break
+
+if not data_present:
+    sys.exit(0)
+
+for key, value in data_args_values.items():
+    col_names = [all_col_names[idx] for idx in data_args_indices_types[key]["indices"]]
+    data_args_values[key] = pd.DataFrame(value, columns=col_names)
+
+# If reference argument (is a Dataset object) present in params, then it contains
+# the prefix of the file path which contains the reference Dataset object.
+if "reference" in params.keys() and params["reference"] is not None:
+    reference_dataset_file_prefix = params["reference"]
+    reference_arg_file_path = f"{reference_dataset_file_prefix}_{partition_join}"\
+                    if is_lake_system else \
+                    f"./{db}/{reference_dataset_file_prefix}_{partition_join}"
+    with open(reference_arg_file_path, "rb") as f:
+        params["reference"] = pickle.load(f)
+
+if not func_name:
+    # Create DataSet object if no function of Dataset class is called.
+    lib = import_module(module_name)
+    class_instance = getattr(lib, class_name)
+    obj = class_instance(**{**data_args_values, **params})
+else:
+    # If function of Dataset object is called, then call the function on model object.
+    with open(model_file_path, "rb") as fp:
+        model = pickle.loads(fp.read())
+
+    if not model:
+        sys.exit("Model file is not installed in Vantage.")
+
+    obj = getattr(model, func_name)(**{**data_args_values, **params})
+
+model_str = pickle.dumps(obj)
+
+if is_lake_system:
+    model_file_path = f"/tmp/{model_file_prefix}_{partition_join}.pickle"
+
+# Save DataSet object to binary file
+with open(model_file_path, "wb") as f:
+    f.write(model_str)
+
+model_data = model_file_path if is_lake_system else base64.b64encode(model_str)
+
+print(*(data_partition_column_values + [model_data]), sep=DELIMITER)

teradataml/data/scripts/lightgbm/lightgbm_class_functions.template

@@ -0,0 +1,247 @@
+import base64
+import io
+import math
+import os
+import pickle
+import sys
+
+import numpy as np
+
+DELIMITER = '\t'
+
+def get_values_list(values, types):
+    ret_vals = []
+    for i, val in enumerate(values):
+        ret_vals.append(convert_to_type(val, types[i]))
+    return ret_vals
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+def should_convert(t_val, py_type):
+    """
+    Function to check type of value and whether value is nan and infinity.
+    """
+    return not isinstance(t_val, eval(py_type)) and not math.isinf(t_val) and not math.isnan(t_val)
+
+def convert_value(t_val, py_type):
+    """
+    Function to convert value to specified python type.
+    """
+    return convert_to_type(t_val, py_type) if should_convert(t_val, py_type) else t_val
+
+# Process output returned by sklearn function.
+def get_output_data(trans_values, func_name, n_c_labels, n_out_columns):
+    # Converting    sparse matrix to dense array as sparse matrices are NOT
+    # supported in Vantage.
+    # module_name = model_obj.__module__.split("._")[0]
+
+    # Converting the translated values into corresponding the return column's 
+    # python type.
+    if (return_columns_python_types is None or not isinstance(trans_values, np.ndarray)):
+        trans_values_list = trans_values
+    else:
+        # Conversion.
+        trans_values_list = []
+        for trans_value in trans_values.tolist():
+            if not isinstance(trans_value, list):
+                trans_value = [trans_value]
+
+            converted_list = []
+            if len(return_columns_python_types) == len(trans_value):
+                for t_val, py_type in zip(trans_value, return_columns_python_types):
+                    converted_list.append(convert_value(t_val, py_type))
+            ## transform() is having only 1 python return type, But it actually returns more than 1 column. 
+            else:
+                for t_val in trans_value:
+                    converted_list.append(convert_value(t_val, return_columns_python_types[0]))
+
+            trans_values_list.append(converted_list)
+
+    if type(trans_values_list).__name__ in ["csr_matrix", "csc_matrix"]:
+        trans_values_list = trans_values_list.toarray()
+
+    if isinstance(trans_values_list[0], np.ndarray) \
+            or isinstance(trans_values_list[0], list) \
+            or isinstance(trans_values_list[0], tuple):
+        # Here, the value returned by sklearn function is list type.
+        opt_list = list(trans_values_list[0])
+
+        if len(opt_list) < n_out_columns:
+            # If the output list is less than the required number of columns, append
+            # empty strings to the list.
+            opt_list += [""] * (n_out_columns - len(opt_list))
+
+        return opt_list
+
+    # Only one element is returned by the function.
+    return [trans_values_list[0]]
+
+# Arguments to the Script
+if len(sys.argv) != 10:
+    # 10 arguments command line arguments should be passed to this file.
+    # 1: file to be run
+    # 2. function name (Eg. predict, fit etc)
+    # 3. No of feature columns.
+    # 4. No of class labels.
+    # 5. Comma separated indices of partition columns.
+    # 6. Comma separated types of all the data columns.
+    # 7. Model file prefix to generated model file using partition columns.
+    # 8. Number of columns to be returned by the sklearn's transform function.
+    # 9. Flag to check the system type. True, means Lake, Enterprise otherwise.
+    # 10. Python types of returned/transfromed columns.
+    sys.exit("10 arguments should be passed to this file - file to be run, function name, "\
+                 "no of feature columns, no of class labels, comma separated indices of partition "\
+                 "columns, comma separated types of all columns, model file prefix to generate model "\
+                 "file using partition columns, number of columns to be returnd by sklearn's "\
+                 "transform function, flag to check lake or enterprise and Python types of "\
+                 "returned/transfromed columns.")
+
+is_lake_system = eval(sys.argv[8])
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+func_name = sys.argv[1]
+n_f_cols = int(sys.argv[2])
+n_c_labels = int(sys.argv[3])
+data_column_types = splitter(sys.argv[5], delim="--")
+data_partition_column_indices = splitter(sys.argv[4], convert_to="int") # indices are integers.
+model_file_prefix = sys.argv[6]
+# sys.argv[9] will contain a string of python datatypes with '--'
+# separator OR a single datatype OR None in string format.
+ret_col_argv = sys.argv[9]
+if ret_col_argv == "None":
+    return_columns_python_types = eval(ret_col_argv)
+else:
+    return_columns_python_types = splitter(ret_col_argv, delim="--")
+
+no_of_output_columns = int(sys.argv[7])
+
+data_partition_column_types = [data_column_types[idx] for idx in data_partition_column_indices]
+
+model = None
+data_partition_column_values = []
+
+all_x_rows = []
+all_y_rows = []
+
+# Data Format:
+# feature1, feature2, ..., featuren, label1, label2, ... labelk, data_partition_column1, ..., 
+# data_partition_columnn.
+# label is optional (it is present when label_exists is not "None")
+
+model_name = ""
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            values = line.split(DELIMITER)
+            values = get_values_list(values, data_column_types)
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}" \
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+                with open(model_file_path, "rb") as fp:
+                    model = pickle.loads(fp.read())
+
+                if not model:
+                    sys.exit("Model file is not installed in Vantage.")
+
+            f_ = values[:n_f_cols]
+            f__ = np.array([f_])
+
+            if n_c_labels > 0:
+                l_ = values[n_f_cols:n_f_cols+n_c_labels]
+                l__ = np.array([l_])
+
+            if func_name == "refit":
+                # refit() needs all data at once. Hence, read all data at once and call refit().
+                all_x_rows.append(f_)
+                all_y_rows.append(l_)
+                continue
+
+            # Because `predict` function does not accept 'y' as input, we need to handle it separately.
+            if n_c_labels > 0 and func_name not in ["predict"]:
+                # Labels are present in last column.
+                trans_values = getattr(model, func_name)(f__, l__, **params)
+            else:
+                # If class labels do not exist in data, don't read labels, read just features.
+                trans_values = getattr(model, func_name)(f__, **params)
+
+            result_list = f_
+            if n_c_labels > 0 and func_name in ["predict", "decision_function"]:
+                result_list += l_
+            result_list += get_output_data(trans_values=trans_values, func_name=func_name,
+                                           n_c_labels=n_c_labels, n_out_columns=no_of_output_columns)
+
+            for i, val in enumerate(result_list):
+                if (val is None or (not isinstance(val, str) and (math.isnan(val) or math.isinf(val)))):
+                    result_list[i] = ""
+                elif val == False:
+                    result_list[i] = 0
+                elif val == True:
+                    result_list[i] = 1
+
+            print(*(data_partition_column_values + result_list), sep=DELIMITER)
+
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break
+
+
+if func_name == "refit":
+    result = ""
+    stdout = None
+    try:
+        stdout = sys.stdout
+        new_stdout = io.StringIO()
+        sys.stdout = new_stdout
+        trained_model = getattr(model, func_name)(all_x_rows, all_y_rows, **params)
+        result = new_stdout.getvalue()
+    except Exception:
+        raise
+    finally:
+        sys.stdout = stdout
+
+    model_str = pickle.dumps(trained_model)
+
+
+    if is_lake_system:
+        model_file_path = f"/tmp/{model_file_prefix}_{partition_join}.pickle"
+
+    # Write to trained model file in Vantage.
+    with open(model_file_path, "wb") as fp:
+        fp.write(model_str)
+
+    model_data = model_file_path if is_lake_system else base64.b64encode(model_str)
+    console_output = base64.b64encode(result.encode())
+
+    print(*(data_partition_column_values + [model_data, console_output]), sep="..")