initial commit

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.9" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/nyc-taxi-model.iml" filepath="$PROJECT_DIR$/.idea/nyc-taxi-model.iml" />
+    </modules>
+  </component>
+</project>

.idea/nyc-taxi-model.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11-slim
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /code
+
+RUN mkdir -p /code/preprocessor && chmod -R 777 /code/preprocessor
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN apt-get update && apt-get install -y procps && pip install -U pip && rm /etc/localtime && ln -s /usr/share/zoneinfo/America/Mexico_City /etc/localtime
+
+RUN pip install -r ./requirements.txt
+
+COPY ./main.py /code/
+
+EXPOSE 8000
+
+CMD ["uvicorn","main:app", "--host", "0.0.0.0", "--port", "8000"]

main.py

@@ -0,0 +1,77 @@
+import pickle
+import mlflow
+from fastapi import FastAPI
+from pydantic import BaseModel
+from mlflow import MlflowClient
+
+
+# MLflow settings
+# dagshub_repo = "url-to-your-repo"
+# dagshub_repo = "https://dagshub.com/zapatacc/nyc-taxi-time-prediction"
+
+# dagshub.init(url=dagshub_repo, mlflow=True)
+
+# MLFLOW_TRACKING_URI = mlflow.get_tracking_uri()
+MLFLOW_TRACKING_URI = "https://dagshub.com/zapatacc/nyc-taxi-time-prediction.mlflow"
+
+mlflow.set_tracking_uri(uri=MLFLOW_TRACKING_URI)
+client = MlflowClient(tracking_uri=MLFLOW_TRACKING_URI)
+
+run_ = mlflow.search_runs(order_by=['metrics.rmse ASC'],
+                          output_format="list",
+                          experiment_names=["nyc-taxi-experiment-prefect"]
+                          )[0]
+
+run_id = run_.info.run_id
+
+run_uri = f"runs:/{run_id}/preprocessor"
+
+client.download_artifacts(
+    run_id=run_id,
+    path='preprocessor',
+    dst_path='.'
+)
+
+with open("preprocessor/preprocessor.b", "rb") as f_in:
+    dv = pickle.load(f_in)
+
+model_name = "nyc-taxi-model"
+alias = "champion"
+
+model_uri = f"models:/{model_name}@{alias}"
+
+champion_model = mlflow.pyfunc.load_model(
+    model_uri=model_uri
+)
+
+def preprocess(input_data):
+
+    input_dict = {
+        'PU_DO': input_data.PULocationID + "_" + input_data.DOLocationID,
+        'trip_distance': input_data.trip_distance,
+    }
+
+    return dv.transform(input_dict)
+
+def predict(input_data):
+
+    X_pred = preprocess(input_data)
+
+    return champion_model.predict(X_pred)
+
+
+app = FastAPI()
+
+class InputData(BaseModel):
+    PULocationID: str
+    DOLocationID: str
+    trip_distance: float
+
+
+@app.post("/predict")
+def predict_endpoint(input_data: InputData):
+    result = predict(input_data)[0]
+
+    return {
+        "prediction": float(result)
+    }

requirements.txt

@@ -0,0 +1,10 @@
+fastapi==0.115.2
+mlflow==2.16.1
+xgboost==2.1.1
+uvicorn
+numpy==2.1.1
+pandas==2.2.2
+psutil==6.0.0
+scikit-learn==1.5.2
+scipy==1.14.1
+xgboost==2.1.1