Added Dockerfile, tests & updated requirements.txt

Dockerfile

@@ -0,0 +1,22 @@
+# Use the official Python image from the Docker Hub
+FROM python:3.12-slim
+
+RUN pip install -U pip
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+COPY setup.py .
+# installs the project in executable mode
+RUN pip install -e .
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose the port the application will run on
+EXPOSE 9696
+
+# Define the entry point for the container
+ENTRYPOINT ["gunicorn", "--bind=0.0.0.0:9696", "app:app"]

Makefile

@@ -22,3 +22,37 @@ clean:
 	# -rmdir /S /Q __pycache__
 
 .PHONY: all preprocess clean ensure_artifacts_dir
+
+
+
+# Makefile for ML Project
+
+# Variables
+TRAIN_DATA_PATH = path/to/train_data.csv
+VALIDATE_DATA_PATH = path/to/validate_data.csv
+TRAIN_SCRIPT = src/components/model_trainer.py
+DATA_INGEST_SCRIPT = src/components/data_ingestion.py
+DATA_PREPROCESS_SCRIPT = src/components/data_preprocessing.py
+
+# Targets
+
+.PHONY: all data_ingest preprocess train clean
+
+all: data_ingest preprocess train
+
+data_ingest:
+	@echo "Running Data Ingestion..."
+	python $(DATA_INGEST_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+
+preprocess: data_ingest
+	@echo "Running Data Preprocessing..."
+	python $(DATA_PREPROCESS_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+
+train: preprocess
+	@echo "Running Model Training..."
+	python $(TRAIN_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+
+clean:
+	@echo "Cleaning up..."
+	rm -rf artifacts/ logs/
+

README.md

@@ -74,7 +74,7 @@ You can install the required packages using the provided`conda_dependencies.yml`
 
 After creating your virtual environment, you can activate it using:
 
-```conda activate myenv // That's is the name specified in the .yml file```
+<codespace/>```conda activate myenv // That's is the name specified in the .yml file```</codespace>
 
 Or using `requirements.txt`:
 

app.py

@@ -2,8 +2,6 @@
 import numpy as np
 import pandas as pd
 
-from sklearn.preprocessing import StandardScaler
-
 from src.pipeline.predict import CustomData, PredictPipeline
 
 app = Flask(__name__)
@@ -25,7 +23,7 @@ def predict_data():
             Aspectratio=request.form.get('Aspectratio'),
             Eccentricity=request.form.get('Eccentricity'),
             Convexarea=request.form.get('Convexarea'),
-            Equivdiameter=request.form.get('Equivdiameter'),	
+            Equivdiameter=request.form.get('Equivdiameter'),
             Extent=request.form.get('Extent'),
             Solidity=request.form.get('Solidity'),
             Roundness=request.form.get('Roundness'),
@@ -40,8 +38,8 @@ def predict_data():
 
         predict_pipeline=PredictPipeline()
         results=predict_pipeline.predict(pred_df)
-        return render_template('home.html', results=results[0])
+        return render_template('home.html', results=results)
 
 
 if __name__=="__main__":
-    app.run(host="0.0.0.0", debug=True)
+    app.run(host="0.0.0.0", debug=True, port=9696)

config/grafana_datasources.yaml

@@ -0,0 +1,15 @@
+apiVersion: 1
+
+# list of datasources that should be added
+# available in the database
+datasources:
+  - name: PostgreSQL
+    type: postgres
+    access: proxy
+    url: db.:5432
+    database: ${POSTGRES_DB}
+    user: ${POSTGRES_USER}
+    secureJsonData:
+      password: ${POSTGRES_PASSWORD}
+    jsonData:
+      sslmode: 'disable'

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/MLmodel

@@ -0,0 +1,40 @@
+artifact_path: xgboost_model
+flavors:
+  python_function:
+    data: model.xgb
+    env:
+      conda: conda.yaml
+      virtualenv: python_env.yaml
+    loader_module: mlflow.xgboost
+    python_version: 3.12.4
+  xgboost:
+    code: null
+    data: model.xgb
+    model_class: xgboost.sklearn.XGBClassifier
+    model_format: xgb
+    xgb_version: 2.1.0
+mlflow_version: 2.15.1
+model_size_bytes: 1219840
+model_uuid: 4f645dacef5d45c0a2cf142cd30d02b8
+run_id: 520470d284b540728611088fe8f69d28
+saved_input_example_info:
+  artifact_path: input_example.json
+  pandas_orient: split
+  serving_input_path: serving_input_payload.json
+  type: dataframe
+signature:
+  inputs: '[{"type": "double", "name": "Area", "required": true}, {"type": "double",
+    "name": "Perimeter", "required": true}, {"type": "double", "name": "MajorAxisLength",
+    "required": true}, {"type": "double", "name": "MinorAxisLength", "required": true},
+    {"type": "double", "name": "AspectRatio", "required": true}, {"type": "double",
+    "name": "Eccentricity", "required": true}, {"type": "double", "name": "ConvexArea",
+    "required": true}, {"type": "double", "name": "EquivDiameter", "required": true},
+    {"type": "double", "name": "Extent", "required": true}, {"type": "double", "name":
+    "Solidity", "required": true}, {"type": "double", "name": "Roundness", "required":
+    true}, {"type": "double", "name": "Compactness", "required": true}, {"type": "double",
+    "name": "ShapeFactor1", "required": true}, {"type": "double", "name": "ShapeFactor2",
+    "required": true}, {"type": "double", "name": "ShapeFactor3", "required": true},
+    {"type": "double", "name": "ShapeFactor4", "required": true}]'
+  outputs: '[{"type": "long", "required": true}]'
+  params: null
+utc_time_created: '2024-08-17 20:20:39.766356'

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/conda.yaml

@@ -0,0 +1,14 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.12.4
+- pip<=24.0
+- pip:
+  - mlflow==2.15.1
+  - numpy==1.26.4
+  - pandas==2.2.2
+  - psutil==5.9.8
+  - scikit-learn==1.5.1
+  - scipy==1.14.0
+  - xgboost==2.1.0
+name: mlflow-env

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/input_example.json

@@ -0,0 +1 @@
+{"columns": ["Area", "Perimeter", "MajorAxisLength", "MinorAxisLength", "AspectRatio", "Eccentricity", "ConvexArea", "EquivDiameter", "Extent", "Solidity", "Roundness", "Compactness", "ShapeFactor1", "ShapeFactor2", "ShapeFactor3", "ShapeFactor4"], "data": [[75351.0, 1095.258, 408.4086836, 236.0432439, 1.730228228, 0.816066202, 76285.0, 309.7416229, 0.794305532, 0.98775644, 0.789343462, 0.758410963, 0.005420083, 0.001106125, 0.575187188, 0.995205109]]}

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/python_env.yaml

@@ -0,0 +1,7 @@
+python: 3.12.4
+build_dependencies:
+- pip==24.0
+- setuptools==69.5.1
+- wheel==0.43.0
+dependencies:
+- -r requirements.txt

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/requirements.txt

@@ -0,0 +1,7 @@
+mlflow==2.15.1
+numpy==1.26.4
+pandas==2.2.2
+psutil==5.9.8
+scikit-learn==1.5.1
+scipy==1.14.0
+xgboost==2.1.0

mlruns/1/520470d284b540728611088fe8f69d28/artifacts/xgboost_model/serving_input_payload.json

@@ -0,0 +1,42 @@
+{
+  "dataframe_split": {
+    "columns": [
+      "Area",
+      "Perimeter",
+      "MajorAxisLength",
+      "MinorAxisLength",
+      "AspectRatio",
+      "Eccentricity",
+      "ConvexArea",
+      "EquivDiameter",
+      "Extent",
+      "Solidity",
+      "Roundness",
+      "Compactness",
+      "ShapeFactor1",
+      "ShapeFactor2",
+      "ShapeFactor3",
+      "ShapeFactor4"
+    ],
+    "data": [
+      [
+        75351.0,
+        1095.258,
+        408.4086836,
+        236.0432439,
+        1.730228228,
+        0.816066202,
+        76285.0,
+        309.7416229,
+        0.794305532,
+        0.98775644,
+        0.789343462,
+        0.758410963,
+        0.005420083,
+        0.001106125,
+        0.575187188,
+        0.995205109
+      ]
+    ]
+  }
+}