перегоняем csv в бд, больше половины успешно пхпхпх

.env

@@ -1,3 +1,8 @@
+DB_USER=postgres
+DB_PASSWORD=password
+DB_HOST=localhost
+DB_PORT=5432
+DB_NAME=test
 DATABASE=SuperService
 POSTGRES_USER=UserSuperService
 POSTGRES_PASSWORD=NotWarningWord1

README.md

@@ -55,8 +55,16 @@ docker exec -it clickhouse-db clickhouse-client -u UserMyHouse --password NotWar
 ```
 USE SuperService;
 ```
-## 7. Подключение к PostgreSQL
+## 8. Подключение к PostgreSQL
 Команда входа в ClickHouse
 ```
 docker exec -it postgres-db psql -U UserSuperService -d SuperService
 ```
+
+## 9. Миграция alembic
+```
+alembic revision --autogenerate
+```
+```
+alembic upgrade head
+```

alembic.ini

@@ -0,0 +1,117 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = db/migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = . db
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to db/migrations/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:db/migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

db/config.py

@@ -7,12 +7,22 @@ class Settings(BaseSettings):
     DB_HOST: str
     DB_PORT: int
     DB_NAME: str
+    DATABASE: str
+    POSTGRES_USER: str
+    POSTGRES_PASSWORD: str
+    CLICKHOUSE_USER: str
+    CLICKHOUSE_PASSWORD: str
 
     @property
     def db_url_asyncpg(self):
         # 'postgresql+asyncpg://username:password@localhost:5432/database_name'
         return f'postgresql+asyncpg://{self.DB_USER}:{self.DB_PASSWORD}@{self.DB_HOST}:{self.DB_PORT}/{self.DB_NAME}'
 
+    @property
+    def db_url_asyncpg_docker(self):
+        # 'postgresql+asyncpg://username:password@localhost:5432/database_name'
+        return f'postgresql+asyncpg://{self.POSTGRES_USER}:{self.POSTGRES_PASSWORD}@db:{self.DB_PORT}/{self.DATABASE}'
+
     model_config = SettingsConfigDict(env_file='../.env')
 
 

db/csv_to_db.py

@@ -1,10 +1,56 @@
 import pandas as pd
+from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker
+from sqlalchemy import insert
+from db.config import settings
+from db.models.base import Base
+from db.models.experiment_data_model import ExperimentData
+from db.models.experiment_parameters_model import ExperimentParameters
+from db.models.load_parameters_model import  LoadParameters
+from db.models.recycling_parameters_model import RecyclingParameters
+import asyncio
+
+engine = create_async_engine(url=settings.db_url_asyncpg, echo=True)
+
+async_session = async_sessionmaker(engine)
 
 
-df = pd.read_csv('./files/recycling_parameters.csv')
-headers = df.columns.tolist()
-print(headers)
 
-for header in headers:
+async def create_all_tables():
-    column_type = df[header].dtype
+    async with engine.begin() as conn:
-    print(column_type)
+        await conn.run_sync(Base.metadata.create_all)
+
+async def drop_all_tables():
+    async with engine.begin() as conn:
+        await conn.run_sync(Base.metadata.drop_all)
+
+
+async def load_data_to_db(file: str, model_class):
+    async with async_session() as session:
+        df = pd.read_csv(file).dropna()
+        # Преобразование данных из DataFrame в формат, подходящий для SQLAlchemy
+        data_records = df.to_dict(orient='records')
+
+        # Пакетная вставка всех записей
+        stmt = insert(model_class).values(data_records)
+        await session.execute(stmt)
+
+        await session.commit()
+
+
+async def main():
+    # await drop_all_tables()
+    # await create_all_tables()
+    await load_data_to_db('./files/experiment_data.csv', ExperimentData)
+    # await load_data_to_db('./files/load_parameters.csv', LoadParameters)
+    # await load_data_to_db('./files/recycling_parameters.csv', RecyclingParameters)
+    # await load_data_to_db('./files/experiment_parameters.csv', ExperimentParameters)
+
+if __name__ == '__main__':
+    asyncio.run(main())
+    # df = pd.read_csv('./files/experiment_data.csv')
+    # headers = df.columns.tolist()
+    # print(headers)
+    #
+    # for header in headers:
+    #     column_type = df[header].dtype
+    #     print(column_type)

db/migrations/env.py

@@ -0,0 +1,74 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+from db.config import settings
+from db.models.experiment_data_model import ExperimentData
+from db.models.experiment_parameters_model import ExperimentParameters
+from db.models.load_parameters_model import  LoadParameters
+from db.models.recycling_parameters_model import RecyclingParameters
+from db.models.base import Base
+
+config = context.config
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+config.set_main_option('sqlalchemy.url', settings.db_url_asyncpg + '?async_fallback=True')
+
+target_metadata = Base.metadata
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

db/migrations/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

db/models/ch_experimentdb_experiment_data_model.py

@@ -1,4 +1,4 @@
-from data_base.db import Base
+from db.models.base import Base
 from sqlalchemy.orm import Mapped, mapped_column
 
 class ChExperimentDBExperimentData(Base):

db/models/experiment_data_model.py

@@ -1,16 +1,18 @@
-from base import Base
+from typing import Optional
+
+from db.models.base import Base
 from sqlalchemy.orm import Mapped, mapped_column
 
 class ExperimentData(Base):
     __tablename__ = 'experiment_data'
 
-    id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
+    id: Mapped[int] = mapped_column(primary_key=True)
     direction: Mapped[float]
     temperature: Mapped[float]
     nox: Mapped[float]
     co2: Mapped[float]
     co: Mapped[float]
-    file_id: Mapped[str]
+    file_id: Mapped[Optional[str]]
 
     def __repr__(self):
         return f"<ExperimentData>"

db/models/experiment_parameters_model.py

@@ -2,17 +2,18 @@ from typing import Optional
 
 from sqlalchemy import ForeignKey
 
-from base import Base
+from db.models.base import Base
 from sqlalchemy.orm import Mapped, mapped_column
 
 class ExperimentParameters(Base):
     __tablename__ = 'experiment_parameters'
 
-    id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
+    id: Mapped[int] = mapped_column(primary_key=True)
     outer_blades_count: Mapped[int]
     outer_blades_length: Mapped[float]
     outer_blades_angle: Mapped[float]
     middle_blades_count: Mapped[int]
+    # load_id: Mapped[int]
     load_id: Mapped[Optional[int]] = mapped_column(ForeignKey('load_parameters.id', ondelete='SET NULL'))
     recycling_id: Mapped[Optional[int]] = mapped_column(ForeignKey('recycling_parameters.id', ondelete='SET NULL'))
     experiment_hash: Mapped[str]

db/models/load_parameters_model.py

@@ -1,10 +1,10 @@
-from base import Base
+from db.models.base import Base
 from sqlalchemy.orm import Mapped, mapped_column
 
 class LoadParameters(Base):
     __tablename__ = 'load_parameters'
 
-    id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
+    id: Mapped[int] = mapped_column(primary_key=True)
     load: Mapped[int]
     primary_air_consumption: Mapped[float]
     secondary_air_consumption: Mapped[float]

db/models/recycling_parameters_model.py

@@ -2,13 +2,13 @@ from typing import Optional
 
 from sqlalchemy import ForeignKey
 
-from base import Base
+from db.models.base import Base
 from sqlalchemy.orm import Mapped, mapped_column
 
 class RecyclingParameters(Base):
     __tablename__ = 'recycling_parameters'
 
-    id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
+    id: Mapped[int] = mapped_column(primary_key=True)
     load_id: Mapped[Optional[int]] = mapped_column(ForeignKey('load_parameters.id', ondelete='SET NULL'))
     recycling_level: Mapped[int]
     co2: Mapped[float]

main.py

@@ -29,3 +29,12 @@ def run_experiment_api(params: ExperimentParameters):
         return {"status": "success", "message": "Experiment started successfully."}
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")
+
+
+@app.post('/init_db_data')
+def init_db_data():
+    try:
+
+        return {"status": "success", "message": "Experiment started successfully."}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")