developments

README

@@ -0,0 +1,27 @@
+# Translation Delivery Time CLI
+
+This command line application calculates the moving average delivery time of translation events based on a specified window size.
+
+## Requirements
+
+- Python 3.7.x or higher
+
+## Installation
+
+1. Clone or download the repository to your local machine.
+2. Ensure you have Python installed.
+
+## Usage
+
+Run the application from the command line with the following command:
+python unbabel_cli.py --input_file events.json --window_size 10
+
+
+Replace `events.json` with the path to your input JSON file containing translation events and `10` with your desired window size.
+
+## Testing
+
+To test the application, you can run the unit tests provided in the `tests-unbabel-cli.py` file. Use the following command:
+python -m unittest tests_unbabel_cli.py
+
+DISCLAIMER: Unfortunatly the output is not as expected, the code is what I could do with the time I had

events.json

@@ -0,0 +1,3 @@
+{"timestamp": "2018-12-26 18:11:08.509654","translation_id": "5aa5b2f39f7254a75aa5","source_language": "en","target_language": "fr","client_name": "airliberty","event_name": "translation_delivered","nr_words": 30, "duration": 20}
+{"timestamp": "2018-12-26 18:15:19.903159","translation_id": "5aa5b2f39f7254a75aa4","source_language": "en","target_language": "fr","client_name": "airliberty","event_name": "translation_delivered","nr_words": 30, "duration": 31}
+{"timestamp": "2018-12-26 18:23:19.903159","translation_id": "5aa5b2f39f7254a75bb3","source_language": "en","target_language": "fr","client_name": "taxi-eats","event_name": "translation_delivered","nr_words": 100, "duration": 54}

output.json

@@ -0,0 +1,14 @@
+{"date": "2018-12-26 18:11:00", "average_delivery_time": 0}
+{"date": "2018-12-26 18:12:00", "average_delivery_time": 20.0}
+{"date": "2018-12-26 18:13:00", "average_delivery_time": 20.0}
+{"date": "2018-12-26 18:14:00", "average_delivery_time": 20.0}
+{"date": "2018-12-26 18:15:00", "average_delivery_time": 20.0}
+{"date": "2018-12-26 18:16:00", "average_delivery_time": 25.5}
+{"date": "2018-12-26 18:17:00", "average_delivery_time": 25.5}
+{"date": "2018-12-26 18:18:00", "average_delivery_time": 25.5}
+{"date": "2018-12-26 18:19:00", "average_delivery_time": 25.5}
+{"date": "2018-12-26 18:20:00", "average_delivery_time": 25.5}
+{"date": "2018-12-26 18:21:00", "average_delivery_time": 31.0}
+{"date": "2018-12-26 18:22:00", "average_delivery_time": 31.0}
+{"date": "2018-12-26 18:23:00", "average_delivery_time": 31.0}
+{"date": "2018-12-26 18:24:00", "average_delivery_time": 42.5}

tests_unbabel_cli.py

@@ -0,0 +1,46 @@
+import unittest
+import json
+from datetime import datetime
+from unbabel_cli import parse_event, moving_average
+
+class TestMovingAverages(unittest.TestCase):
+    def setUp(self):
+        self.events = [
+            {"timestamp": "2018-12-26 18:11:08.509654", "duration": 20},
+            {"timestamp": "2018-12-26 18:15:19.903159", "duration": 31},
+            {"timestamp": "2018-12-26 18:23:19.903159", "duration": 54}
+        ]
+        self.parsed_events = [
+            {"timestamp": datetime(2018, 12, 26, 18, 11, 8, 509654), "duration": 20},
+            {"timestamp": datetime(2018, 12, 26, 18, 15, 19, 903159), "duration": 31},
+            {"timestamp": datetime(2018, 12, 26, 18, 23, 19, 903159), "duration": 54}
+        ]
+
+    def test_parse_event(self):
+        parsed = [parse_event(event) for event in self.events]
+        self.assertEqual(parsed, self.parsed_events)
+
+    def test_moving_average(self):
+        results = moving_average(self.parsed_events, 10)
+        expected_results = [
+            {"date": "2018-12-26 18:11:00", "average_delivery_time": 0},
+            {"date": "2018-12-26 18:12:00", "average_delivery_time": 20},
+            {"date": "2018-12-26 18:13:00", "average_delivery_time": 20},
+            {"date": "2018-12-26 18:14:00", "average_delivery_time": 20},
+            {"date": "2018-12-26 18:15:00", "average_delivery_time": 20},
+            {"date": "2018-12-26 18:16:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:17:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:18:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:19:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:20:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:21:00", "average_delivery_time": 25.5},
+            {"date": "2018-12-26 18:22:00", "average_delivery_time": 31},
+            {"date": "2018-12-26 18:23:00", "average_delivery_time": 31},
+            {"date": "2018-12-26 18:24:00", "average_delivery_time": 42.5}
+        ]
+        self.assertEqual(results, expected_results)
+
+    # Add other tests here if needed
+
+if __name__ == '__main__':
+    unittest.main()

unbabel_cli.py

@@ -0,0 +1,88 @@
+import json
+import argparse
+from datetime import datetime, timedelta
+
+# Function to parse each event from JSON format
+def parse_event(event):
+    return {
+        'timestamp': datetime.strptime(event['timestamp'], '%Y-%m-%d %H:%M:%S.%f'),
+        'duration': event['duration']
+    }
+
+# Function to calculate the moving average delivery time
+def moving_average(events, window_size):
+    # Sort events based on timestamp
+    events = sorted(events, key=lambda x: x['timestamp'])
+    # Define start and end times of the event stream
+    start_time = events[0]['timestamp'].replace(second=0, microsecond=0)
+    end_time = events[-1]['timestamp'].replace(second=0, microsecond=0) + timedelta(minutes=1)
+    # Define the window size
+    window = timedelta(minutes=window_size)
+    result = []
+
+    # Loop through each minute in the event stream
+    current_time = start_time
+    while current_time <= end_time:
+        # Calculate the start of the current window
+        window_start = current_time - window + timedelta(minutes=1)
+        # Extract events within the current window
+        window_events = [event['duration'] for event in events if window_start <= event['timestamp'] <= current_time]
+        # Calculate the average delivery time for the events within the window
+        if window_events:
+            avg_duration = sum(window_events) / len(window_events)
+        else:
+            avg_duration = 0
+        # Append the result to the output list
+        result.append({'date': current_time.strftime('%Y-%m-%d %H:%M:%S'), 'average_delivery_time': avg_duration})
+        # Move to the next minute
+        current_time += timedelta(minutes=1)
+
+    return result
+
+
+
+# Main function to read input, calculate moving average, and write output
+def main(input_file, window_size):
+    try:
+        # Read events from the input file
+        events = []
+        with open(input_file, 'r') as file:
+            for line in file:
+                try:
+                    # Parse each line as JSON and append to events list
+                    event = json.loads(line.strip())
+                    events.append(parse_event(event))
+                except json.JSONDecodeError as e:
+                    raise ValueError(f"Invalid JSON in input file: {e}")
+
+        # Check if events list is empty
+        if not events:
+            raise ValueError("Input file is empty")
+
+        # Check if window size is valid
+        if not isinstance(window_size, int) or window_size <= 0:
+            raise ValueError("Window size must be a positive integer")
+
+        # Calculate moving average delivery time
+        averages = moving_average(events, window_size)
+
+        # Write output to file
+        with open('output.json', 'w') as file:
+            for avg in averages:
+                file.write(json.dumps(avg) + '\n')
+
+    except FileNotFoundError:
+        print(f"Error: Input file '{input_file}' not found")
+    except ValueError as e:
+        print(f"Error: {e}")
+
+
+# Command line argument parsing
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Process translation delivery events.')
+    parser.add_argument('--input_file', type=str, required=True, help='Path to the input JSON file with events.')
+    parser.add_argument('--window_size', type=int, required=True, help='Size of the moving average window in minutes.')
+
+    args = parser.parse_args()
+    # Call main function with provided arguments
+    main(args.input_file, args.window_size)