feat: initialize ML pipeline project with API, training, and monitoring components

- Add core pipeline scripts for ingestion, training, scoring, deployment, diagnostics, and reporting
- Implement Flask API (`app.py`, `wsgi.py`) and API calling utilities (`apicalls.py`)
- Include configuration file (`config.json`) and project dependencies (`requirements.txt`)
- Add datasets for source, practice, and test scenarios
- Add end-to-end pipeline runner (`fullprocess.py`)
- Include project metadata files (`.gitignore`, LICENSE)

Author: ruddyscent

.gitignore

@@ -0,0 +1,46 @@
+Copyright © 2012 - 2026, Udacity, Inc.
+
+Udacity hereby grants you a license in and to the Educational Content, including
+but not limited to homework assignments, programming assignments, code samples,
+and other educational materials and tools (as further described in the Udacity
+Terms of Use), subject to, as modified herein, the terms and conditions of the
+Creative Commons Attribution-NonCommercial- NoDerivs 3.0 License located at
+http://creativecommons.org/licenses/by-nc-nd/4.0 and successor locations for
+such license (the "CC License") provided that, in each case, the Educational
+Content is specifically marked as being subject to the CC License.
+
+Udacity expressly defines the following as falling outside the definition of
+"non-commercial":
+(a) the sale or rental of (i) any part of the Educational Content, (ii) any
+    derivative works based at least in part on the Educational Content, or (iii)
+    any collective work that includes any part of the Educational Content;
+(b) the sale of access or a link to any part of the Educational Content without
+    first obtaining informed consent from the buyer (that the buyer is aware
+    that the Educational Content, or such part thereof, is available at the
+    Website free of charge);
+(c) providing training, support, or editorial services that use or reference the
+    Educational Content in exchange for a fee;
+(d) the sale of advertisements, sponsorships, or promotions placed on the
+    Educational Content, or any part thereof, or the sale of advertisements,
+    sponsorships, or promotions on any website or blog containing any part of
+    the Educational Material, including without limitation any "pop-up
+    advertisements";
+(e) the use of Educational Content by a college, university, school, or other
+    educational institution for instruction where tuition is charged; and
+(f) the use of Educational Content by a for-profit corporation or non-profit
+    entity for internal professional development or training.
+
+THE SERVICES AND ONLINE COURSES (INCLUDING ANY CONTENT) ARE PROVIDED "AS IS" AND
+"AS AVAILABLE" WITH NO REPRESENTATIONS OR WARRANTIES OF ANY KIND, EITHER
+EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. YOU
+ASSUME TOTAL RESPONSIBILITY AND THE ENTIRE RISK FOR YOUR USE OF THE SERVICES,
+ONLINE COURSES, AND CONTENT. WITHOUT LIMITING THE FOREGOING, WE DO NOT WARRANT
+THAT (A) THE SERVICES, WEBSITES, CONTENT, OR THE ONLINE COURSES WILL MEET YOUR
+REQUIREMENTS OR EXPECTATIONS OR ACHIEVE THE INTENDED PURPOSES, (B) THE WEBSITES
+OR THE ONLINE COURSES WILL NOT EXPERIENCE OUTAGES OR OTHERWISE BE UNINTERRUPTED,
+TIMELY, SECURE OR ERROR-FREE, (C) THE INFORMATION OR CONTENT OBTAINED THROUGH
+THE SERVICES, SUCH AS CHAT ROOM SERVICES, WILL BE ACCURATE, COMPLETE, CURRENT,
+ERROR- FREE, COMPLETELY SECURE OR RELIABLE, OR (D) THAT DEFECTS IN OR ON THE
+SERVICES OR CONTENT WILL BE CORRECTED. YOU ASSUME ALL RISK OF PERSONAL INJURY,
+INCLUDING DEATH AND DAMAGE TO PERSONAL PROPERTY, SUSTAINED FROM USE OF SERVICES.

LICENSE

@@ -0,0 +1,20 @@
+import requests
+
+#Specify a URL that resolves to your workspace
+URL = "http://127.0.0.1/"
+
+
+
+#Call each API endpoint and store the responses
+response1 = #put an API call here
+response2 = #put an API call here
+response3 = #put an API call here
+response4 = #put an API call here
+
+#combine all API responses
+responses = #combine reponses here
+
+#write the responses to your workspace
+
+
+

apicalls.py

@@ -0,0 +1,50 @@
+from flask import Flask, session, jsonify, request
+import pandas as pd
+import numpy as np
+import pickle
+import create_prediction_model
+import diagnosis 
+import predict_exited_from_saved_model
+import json
+import os
+
+
+
+######################Set up variables for use in our script
+app = Flask(__name__)
+app.secret_key = '1652d576-484a-49fd-913a-6879acfa6ba4'
+
+with open('config.json','r') as f:
+    config = json.load(f) 
+
+dataset_csv_path = os.path.join(config['output_folder_path']) 
+
+prediction_model = None
+
+
+#######################Prediction Endpoint
+@app.route("/prediction", methods=['POST','OPTIONS'])
+def predict():        
+    #call the prediction function you created in Step 3
+    return #add return value for prediction outputs
+
+#######################Scoring Endpoint
+@app.route("/scoring", methods=['GET','OPTIONS'])
+def stats():        
+    #check the score of the deployed model
+    return #add return value (a single F1 score number)
+
+#######################Summary Statistics Endpoint
+@app.route("/summarystats", methods=['GET','OPTIONS'])
+def stats():        
+    #check means, medians, and modes for each column
+    return #return a list of all calculated summary statistics
+
+#######################Diagnostics Endpoint
+@app.route("/diagnostics", methods=['GET','OPTIONS'])
+def stats():        
+    #check timing and percent NA values
+    return #add return value for all diagnostics
+
+if __name__ == "__main__":    
+    app.run(host='0.0.0.0', port=8000, debug=True, threaded=True)

app.py

@@ -0,0 +1 @@
+{ "input_folder_path": "practicedata", "output_folder_path": "ingesteddata", "test_data_path": "testdata", "output_model_path": "practicemodels", "prod_deployment_path": "production_deployment"}

config.json

@@ -0,0 +1,27 @@
+from flask import Flask, session, jsonify, request
+import pandas as pd
+import numpy as np
+import pickle
+import os
+from sklearn import metrics
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+import json
+
+
+
+##################Load config.json and correct path variable
+with open('config.json','r') as f:
+    config = json.load(f) 
+
+dataset_csv_path = os.path.join(config['output_folder_path']) 
+prod_deployment_path = os.path.join(config['prod_deployment_path']) 
+
+
+####################function for deployment
+def store_model_into_pickle(model):
+    #copy the latest pickle file, the latestscore.txt value, and the ingestfiles.txt file into the deployment directory
+        
+        
+        
+

deployment.py

@@ -0,0 +1,45 @@
+
+import pandas as pd
+import numpy as np
+import timeit
+import os
+import json
+
+##################Load config.json and get environment variables
+with open('config.json','r') as f:
+    config = json.load(f) 
+
+dataset_csv_path = os.path.join(config['output_folder_path']) 
+test_data_path = os.path.join(config['test_data_path']) 
+
+##################Function to get model predictions
+def model_predictions():
+    #read the deployed model and a test dataset, calculate predictions
+    return #return value should be a list containing all predictions
+
+##################Function to get summary statistics
+def dataframe_summary():
+    #calculate summary statistics here
+    return #return value should be a list containing all summary statistics
+
+##################Function to get timings
+def execution_time():
+    #calculate timing of training.py and ingestion.py
+    return #return a list of 2 timing values in seconds
+
+##################Function to check dependencies
+def outdated_packages_list():
+    #get a list of 
+
+
+if __name__ == '__main__':
+    model_predictions()
+    dataframe_summary()
+    execution_time()
+    outdated_packages_list()
+
+
+
+
+
+    

diagnostics.py

@@ -0,0 +1,40 @@
+
+
+import training
+import scoring
+import deployment
+import diagnostics
+import reporting
+
+##################Check and read new data
+#first, read ingestedfiles.txt
+
+#second, determine whether the source data folder has files that aren't listed in ingestedfiles.txt
+
+
+
+##################Deciding whether to proceed, part 1
+#if you found new data, you should proceed. otherwise, do end the process here
+
+
+##################Checking for model drift
+#check whether the score from the deployed model is different from the score from the model that uses the newest ingested data
+
+
+##################Deciding whether to proceed, part 2
+#if you found model drift, you should proceed. otherwise, do end the process here
+
+
+
+##################Re-deployment
+#if you found evidence for model drift, re-run the deployment.py script
+
+##################Diagnostics and reporting
+#run diagnostics.py and reporting.py for the re-deployed model
+
+
+
+
+
+
+

fullprocess.py

@@ -0,0 +1,26 @@
+import pandas as pd
+import numpy as np
+import os
+import json
+from datetime import datetime
+
+
+
+
+#############Load config.json and get input and output paths
+with open('config.json','r') as f:
+    config = json.load(f) 
+
+input_folder_path = config['input_folder_path']
+output_folder_path = config['output_folder_path']
+
+
+
+#############Function for data ingestion
+def merge_multiple_dataframe():
+    #check for datasets, compile them together, and write to an output file
+
+
+
+if __name__ == '__main__':
+    merge_multiple_dataframe()