MongoDB task based on Aggregation

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N801" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (mongo_aggregate_task)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/mongo_aggregate_task.iml" filepath="$PROJECT_DIR$/.idea/mongo_aggregate_task.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/mongo_aggregate_task.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

app.py

+import uvicorn
+
+from scripts.config.application_config import server_path, port_no
+
+if __name__ == "__main__":
+    try:
+        uvicorn.run(server_path, port=int(port_no), reload=True)
+    except Exception as e:
+        print(str(e))

conf/application.conf

+[server]
+server_path=scripts.services.main:app
+port_no=8000
+[mongo]
+uri=mongodb://localhost:27017
+[file_path]
+path=temp/inspection.json

scripts/config/application_config.py

+import configparser
+
+try:
+    config = configparser.ConfigParser()
+    config.read("conf/application.conf")
+    server_path = config.get("server", "server_path")
+    port_no = config.get("server", "port_no")
+    uri = config.get("mongo", "uri")
+    file_path = config.get("file_path", "path")
+except configparser.NoOptionError:
+    print("could not find conf file")

scripts/constants/db_connection.py

+from pymongo import MongoClient
+
+from scripts.config.application_config import uri
+
+
+def db_connect():
+    try:
+        conn = MongoClient(uri)
+        database = conn["Company"]
+        dblist = conn.list_database_names()
+        if database in dblist:
+            print("database with same name already exist")
+        print("database created successfully")
+        return database
+    except Exception as e:
+        print(str(e))
+

scripts/core/engine/model/company.py

+from typing import List
+
+from pydantic import BaseModel
+
+
+class Address(BaseModel):
+    city: str
+    zip: int
+    street: str
+    number: int
+
+
+class CompanyItem(BaseModel):
+    id: str
+    certificate_number: str
+    business_name: str
+    date: str
+    result: str
+    sector: str
+    address: Address
+
+
+class Model(BaseModel):
+    Company: List[CompanyItem]

scripts/core/handlers/create_excel_file.py

+import json
+
+import pandas as pd
+
+from scripts.config.application_config import file_path
+
+
+def create_excel_file():
+    try:
+        with open(file_path) as data:
+            file_data = json.load(data)
+        df = pd.DataFrame(file_data, columns=["business_name", "result", "date"])
+        df.to_excel("temp/excel_data.xlsx", index=False)
+    except Exception as e:
+        print(str(e))

scripts/services/main.py

+import json
+
+from fastapi import FastAPI, UploadFile
+
+from scripts.config.application_config import file_path
+from scripts.constants.db_connection import db_connect
+from scripts.core.handlers.create_excel_file import create_excel_file
+from scripts.utils.mongo_utils import create_collection
+
+app = FastAPI()
+# create database
+db = db_connect()
+# create collection
+inspection = create_collection(db)
+
+
+@app.get("/", tags=["root"])
+async def root():
+    return {"data": "Mongo aggregation task"}
+
+
+# # upload file from user directory
+# @app.post("/upload", tags=["file upload"])
+# async def file_upload(file: UploadFile):
+#     dataset = file.file.read()
+#     file_data = dataset.decode()
+#     # print(file_data)
+#     return {"file": file}
+
+
+# insert json data into database
+@app.post("/insert_json", tags=["insert JSON"])
+async def insert_data():
+    try:
+        with open(file_path) as data:
+            file_data = json.load(data)
+            inspection.insert_many(file_data)
+        return {"data": "JSON data successfully inserted"}
+    except Exception as e:
+        print(str(e))
+
+
+@app.get("/business_name with max violation issued", tags=["tasks"])
+async def max_violation():
+    try:
+        pipeline = [
+            {
+                '$group': {
+                    '_id': '$business_name',
+                    'count': {
+                        '$sum': 1
+                    }
+                }
+            },
+            {
+                '$sort':
+                    {
+                        'count': -1
+                    }
+            },
+            {
+                '$limit': 1
+            },
+            {
+                '$project':
+                    {
+                        'business_name': '$_id',
+                        '_id': 0
+                    }
+            }
+        ]
+        result = list(inspection.aggregate(pipeline))
+        print(result)
+        return {"data": result}
+    except Exception as e:
+        print(str(e))
+
+
+@app.get("/business name with no violation", tags=["tasks"])
+async def no_violation():
+    try:
+        pipeline = [
+            {
+                '$match': {
+                    'result': 'No violation issued'
+                }
+            }, {
+                '$group': {
+                    '_id': '$business_name'
+                }
+            }, {
+                '$project': {
+                    'business_name': '$_id',
+                    '_id': 0
+                }
+            }
+        ]
+        result = list(inspection.aggregate(pipeline))
+        print(result)
+        return {"data": result}
+    except Exception as e:
+        print(str(e))
+
+
+# create Excel file
+@app.get("/convert_to_excel")
+async def convert_excel():
+    create_excel_file()
+    return {"data", "Excel file generated based on business name,result and date"}

scripts/utils/mongo_utils.py

+def create_collection(db):
+    try:
+        collection_name = "inspection"
+        collection = db[collection_name]
+        print("collection inspection created ")
+        return collection
+    except Exception as e:
+        print(str(e))

temp/inspection.json

+[
+  {
+    "id": "10021-2015-ENFO",
+    "certificate_number": "9278806",
+    "business_name": "ATLIXCO DELI GROCERY INC.",
+    "date": "feb 20 2015",
+    "result": "No violation issued",
+    "sector": "Cigarette Retail Dealer -127",
+    "address": {
+      "city": "Ridgewood",
+      "zip": 11385,
+      "street": "Menahan ST",
+      "number": 1712
+    }
+  },
+     {
+    "id": "10022-2015-ENFO",
+    "certificate_number": "9278807",
+    "business_name": "KL Export INC.",
+    "date": "sep 30 2016",
+    "result": "No violation issued",
+    "sector": "Gadgets Retail Dealer",
+    "address": {
+      "city": "San Francisco",
+      "zip": 11387,
+      "street": " Chinatown ST",
+      "number": 1714
+    }
+  },
+     {
+    "id": "10023-2015-ENFO",
+    "certificate_number": "9278808",
+    "business_name": "SR Import INC.",
+    "date": "Jun 30 2017",
+    "result": "No violation issued",
+    "sector": "Shipping Dealer -128",
+    "address": {
+      "city": "Bengaluru",
+      "zip": 690651,
+      "street": " Neeladri ST",
+      "number": 1715
+    }
+  },
+     {
+    "id": "10024-2020-ENFO",
+    "certificate_number": "9278809",
+    "business_name": "TK Solution PVT LTD",
+    "date": "jan 30 2020",
+    "result": "Violation issued",
+    "sector": "Software Solution",
+    "address": {
+      "city": "Kasaragod",
+      "zip": 671541,
+      "street": "Paduppu",
+      "number": 1717
+    }
+  },
+   {
+    "id": "10025-2018-ENFO",
+    "certificate_number": "9278810",
+    "business_name": "KL Export INC.",
+    "date": "jan 30 2016",
+    "result": "Violation issued",
+    "sector": "Software Solution",
+    "address": {
+      "city": "Berlin",
+      "zip": 625232,
+      "street": "church ST",
+      "number": 1714
+    }
+  },
+    {
+    "id": "10025-2018-ENFO",
+    "certificate_number": "9278810",
+    "business_name": "KL Export INC.",
+    "date": "Dec 20 2017",
+    "result": "Violation issued",
+    "sector": "Software Solution",
+    "address": {
+      "city": "Berlin",
+      "zip": 625232,
+      "street": "church ST",
+      "number": 1714
+    }
+  }
+]
\ No newline at end of file