Upload 6 files

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3.11.9-slim
+
+# Copy requirements file
+COPY requirements.txt .
+
+# Update pip
+RUN pip --timeout=3000 install --no-cache-dir --upgrade pip
+
+# Install dependecies
+RUN pip --timeout=3000 install --no-cache-dir -r requirements.txt
+
+# Make project directory
+RUN mkdir -p /api/
+
+# Set working directory
+WORKDIR /api
+
+# Copy API
+COPY . .
+
+# Expose app port
+EXPOSE 7860
+
+# Start application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,177 @@
+import os
+from dotenv import load_dotenv
+
+from collections.abc import AsyncIterator
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI, Query
+from fastapi.responses import FileResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi_cache import FastAPICache
+from fastapi_cache.backends.inmemory import InMemoryBackend
+from fastapi_cache.coder import PickleCoder
+from fastapi_cache.decorator import cache
+import logging
+
+from pydantic import BaseModel, Field
+from typing import List, Union, Optional
+from datetime import datetime
+
+from sklearn.pipeline import Pipeline
+import joblib
+
+import pandas as pd
+
+import httpx
+from io import BytesIO
+
+
+from utils.config import (
+    ONE_DAY_SEC,
+    ONE_WEEK_SEC,
+    ENV_PATH,
+    DESCRIPTION,
+    ALL_MODELS
+)
+
+load_dotenv(ENV_PATH)
+
+
+@asynccontextmanager
+async def lifespan(_: FastAPI) -> AsyncIterator[None]:
+    FastAPICache.init(InMemoryBackend())
+    yield
+
+
+# FastAPI Object
+app = FastAPI(
+    title='Yassir Eta Prediction',
+    version='1.0.0',
+    description=DESCRIPTION,
+    lifespan=lifespan,
+)
+
+app.mount("/assets", StaticFiles(directory="assets"), name="assets")
+
+
+@app.get('/favicon.ico', include_in_schema=False)
+@cache(expire=ONE_WEEK_SEC, namespace='eta_favicon')  # Cache for 1 week
+async def favicon():
+    file_name = "favicon.ico"
+    file_path = os.path.join(app.root_path, "assets", file_name)
+    return FileResponse(path=file_path, headers={"Content-Disposition": "attachment; filename=" + file_name})
+
+
+# API input features
+
+
+class EtaFeatures(BaseModel):
+    timestamp: List[datetime] = Field(
+        description="Timestamp: Time that the trip was started")
+    origin_lat: List[float] = Field(
+        description="Origin_lat: Origin latitude (in degrees)")
+    origin_lon: List[float] = Field(
+        description="Origin_lon: Origin longitude (in degrees)")
+    destination_lat: List[float] = Field(
+        description="Destination_lat: Destination latitude (in degrees)")
+    destination_lon: List[float] = Field(
+        description="Destination_lon: Destination longitude (in degrees)")
+    trip_distance: List[float] = Field(
+        description="Trip_distance: Distance in meters on a driving route")
+
+
+class Url(BaseModel):
+    url: str
+    pipeline_url: str
+
+
+class ResultData(BaseModel):
+    prediction: List[float]
+
+
+class PredictionResponse(BaseModel):
+    execution_msg: str
+    execution_code: int
+    result: ResultData
+
+
+class ErrorResponse(BaseModel):
+    execution_msg: str
+    execution_code: int
+    error: Optional[str]
+
+
+logging.basicConfig(level=logging.ERROR,
+                    format='%(asctime)s - %(levelname)s - %(message)s')
+
+
+# Load the model pipelines and encoder
+# Cache for 1 day
+@cache(expire=ONE_DAY_SEC, namespace='pipeline_resource', coder=PickleCoder)
+async def load_pipeline(pipeline_url: Url) -> Pipeline:
+    async def url_to_data(url: Url):
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url)
+            response.raise_for_status()  # Ensure we catch any HTTP errors
+            # Convert response content to BytesIO object
+            data = BytesIO(response.content)
+            return data
+
+    pipeline = None
+    try:
+        pipeline: Pipeline = joblib.load(await url_to_data(pipeline_url))
+    except Exception as e:
+        logging.error(
+            "Omg, an error occurred in loading the pipeline resources: %s", e)
+    finally:
+        return pipeline
+
+
+# Endpoints
+
+# Status endpoint: check if api is online
+@app.get('/')
+@cache(expire=ONE_WEEK_SEC, namespace='eta_status_check')  # Cache for 1 week
+async def status_check():
+    return {"Status": "API is online..."}
+
+
+@cache(expire=ONE_DAY_SEC, namespace='pipeline_regressor')  # Cache for 1 day
+async def pipeline_regressor(pipeline: Pipeline, data: EtaFeatures) -> Union[ErrorResponse, PredictionResponse]:
+    msg = 'Execution failed'
+    code = 0
+    output = ErrorResponse(**{'execution_msg': msg,
+                              'execution_code': code, 'error': None})
+
+    try:
+        # Create dataframe
+        df = pd.DataFrame.from_dict(data.__dict__)
+
+        # Make prediction
+        preds = pipeline.predict(df)
+        predictions = [float(pred) for pred in preds]
+
+        result = ResultData(**{"prediction": predictions})
+
+        msg = 'Execution was successful'
+        code = 1
+        output = PredictionResponse(
+            **{'execution_msg': msg,
+               'execution_code': code, 'result': result}
+        )
+
+    except Exception as e:
+        error = f"Omg, pipeline regressor failure. {e}"
+        output = ErrorResponse(**{'execution_msg': msg,
+                                  'execution_code': code, 'error': error})
+
+    finally:
+        return output
+
+
+@app.post('/api/v1/eta/prediction', tags=['All Models'])
+async def query_eta_prediction(data: EtaFeatures, model: str = Query('RandomForestRegressor', enum=list(ALL_MODELS.keys()))) -> Union[ErrorResponse, PredictionResponse]:
+    pipeline_url: Url = ALL_MODELS[model]
+    pipeline = await load_pipeline(pipeline_url)
+    output = await pipeline_regressor(pipeline, data)
+    return output

requirements.txt

@@ -0,0 +1,126 @@
+annotated-types==0.7.0
+anyio==4.4.0
+appdirs==1.4.4
+asgiref==3.8.1
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==24.1.0
+branca==0.7.2
+cattrs==23.2.3
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+comm==0.2.2
+contourpy==1.2.1
+cycler==0.12.1
+debugpy==1.8.2
+decorator==5.1.1
+exceptiongroup==1.2.2
+executing==2.0.1
+faicons==0.2.2
+fastapi==0.112.0
+fastapi-cache2==0.2.2
+fastjsonschema==2.20.0
+fonttools==4.53.1
+geodatasets==2024.7.0
+geographiclib==2.0
+geojson==3.1.0
+geopandas==1.0.1
+geopy==2.4.1
+h11==0.14.0
+htmltools==0.5.3
+httpcore==1.0.5
+httpx==0.27.0
+idna==3.7
+importlib_metadata==8.2.0
+# ipykernel==6.29.5
+# ipyleaflet==0.19.2
+# ipython==8.18.0
+# ipywidgets==8.1.3
+jedi==0.19.1
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+# jupyter_client==8.6.2
+# jupyter_core==5.7.2
+# jupyter-leaflet==0.19.2
+# jupyterlab_widgets==3.0.11
+kiwisolver==1.4.5
+linkify-it-py==2.0.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+# matplotlib==3.9.1
+# matplotlib-inline==0.1.7
+mdit-py-plugins==0.4.1
+mdurl==0.1.2
+# nbformat==5.10.4
+nest_asyncio==1.6.0
+numpy==1.26.4
+packaging==24.1
+pandas==2.2.2
+parso==0.8.4
+patsy==0.5.6
+pendulum==3.0.0
+pickleshare==0.7.5
+pillow==10.4.0
+# pip==24.0
+platformdirs==4.2.2
+# plotly==5.23.0
+# plotly_calplot==0.1.20
+pooch==1.8.2
+prompt-toolkit==3.0.36
+psutil==6.0.0
+pure_eval==0.2.3
+pydantic==2.8.2
+pydantic_core==2.20.1
+Pygments==2.18.0
+PyJWT==2.9.0
+pyogrio==0.9.0
+pyparsing==3.1.2
+pyproj==3.6.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2023.4
+# pywin32==306
+pyzmq==26.0.3
+questionary==2.0.1
+referencing==0.35.1
+requests==2.32.3
+requests-cache==1.2.1
+rpds-py==0.19.1
+rsconnect_python==1.24.0
+scikit-learn==1.5.1
+scipy==1.14.0
+semver==2.13.0
+setuptools==71.0.4
+shapely==2.0.5
+shiny==1.0.0
+shinywidgets==0.3.2
+six==1.16.0
+sniffio==1.3.1
+stack-data==0.6.2
+starlette==0.37.2
+statsmodels==0.14.2
+tenacity==9.0.0
+threadpoolctl==3.5.0
+time-machine==2.15.0
+tornado==6.4.1
+traitlets==5.14.3
+traittypes==0.2.1
+typing_extensions==4.12.2
+tzdata==2024.1
+uc-micro-py==1.0.3
+url-normalize==1.4.3
+urllib3==2.2.2
+uvicorn==0.30.4
+watchfiles==0.22.0
+wcwidth==0.2.13
+websockets==12.0
+wheel==0.43.0
+widgetsnbextension==4.0.11
+xgboost==2.1.1
+xyzservices==2024.6.0
+zipp==3.19.2

utils/config.py

@@ -0,0 +1,73 @@
+from pathlib import Path
+
+# ENV when using standalone uvicorn server running FastAPI in api directory
+ENV_PATH = Path("../env/online.env")
+
+ONE_DAY_SEC = 24*60*60
+
+ONE_WEEK_SEC = ONE_DAY_SEC*7
+
+PIPELINE_FUNCTION_URL = ""
+
+RANDOM_FOREST_URL = "https://drive.google.com/uc?export=download&id=1t0RRzAbtW7Y1lAz4ddB5iY_0SIpfdHbB"
+
+XGBOOST_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/XGBRegressor.joblib"
+
+ADABOOST_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/AdaBoostRegressor.joblib"
+
+GRADIENT_BOOST_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/GradientBoostingRegressor.joblib"
+
+HISTGRADIENT_BOOST_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/HistGradientBoostingRegressor.joblib"
+
+DECISION_TREE_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/DecisionTreeRegressor.joblib"
+
+LINEAR_REG_URL = "https://raw.githubusercontent.com/valiantezabuku/Yassir-ETA-Prediction-Challenge-For-Azubian-Team-Curium/main/Models/LinearRegression.joblib"
+
+
+ALL_MODELS = {
+    "AdaBoostRegressor": ADABOOST_URL,
+    "DecisionTreeRegressor": DECISION_TREE_URL,
+    "GradientBoostingRegressor": GRADIENT_BOOST_URL,
+    "HistGradientBoostingRegressor": HISTGRADIENT_BOOST_URL,
+    "LinearRegression": LINEAR_REG_URL,
+    "RandomForestRegressor": RANDOM_FOREST_URL,
+    "XGBRegressor": XGBOOST_URL
+}
+
+DESCRIPTION = """
+This API accurately predicts the estimated time of arrival at the dropoff point for a single Yassir journey using `Random Forest model` and `XGBoost model`.\n
+
+The models were trained on [The Yassir Eta datasets at Zindi Africa](https://zindi.africa/competitions/yassir-eta-prediction-challenge-for-azubian/data).\n
+
+### Features
+`Timestamp:` Time that the trip was started\n
+`Origin_lat:` Origin latitude (in degrees)\n
+`Origin_lon:` Origin longitude (in degrees)\n
+`Destination_lat:` Destination latitude (in degrees)\n
+`Destination_lon:` Destination longitude (in degrees)\n
+`Trip_distance:` Distance in meters on a driving route\n
+
+#### Weather Features
+Daily weather summaries, based on data from the ERA5 dataset.\n
+`date:` ..\n
+`dewpoint_2m_temperature:` ..\n
+`maximum_2m_air_temperature:` ..\n
+`mean_2m_air_temperature:` ..\n
+`mean_sea_level_pressure:` ..\n
+`minimum_2m_air_temperature:` ..\n
+`surface_pressure:` ..\n
+`total_precipitation:` ..\n
+`u_component_of_wind_10m:` ..\n
+`v_component_of_wind_10m:` ..\n
+ 
+### Results 
+**ETA prediction:** Estimated trip time in seconds\n
+
+
+### Explore the frontend data application
+To explore the fontend application (built-with streamlit) click the link below.\n
+🚗[Yassir frontend](/https://hugginface-yassir)
+
+
+Made with 💖 [Team Curium](#) 
+"""