Added similarity calculations

app.py

@@ -11,7 +11,7 @@ from pydantic import BaseModel
 from fastapi import Query
 from transformers import pipeline
 
-from helper import generate_random_predictions
+from helper import generate_random_predictions, get_sample_similarity_attr
 
 app = FastAPI()
 
@@ -89,20 +89,22 @@ def get_prediction_from_jobrun():
 
 classifier = pipeline("sentiment-analysis")  # Defaults to distilbert-base-uncased-finetuned-sst-2-english
 
+# Define input schema
+class InputText(BaseModel):
+    text: str  # Expect JSON request body with a "text" field
+
 @app.post("/get_sentiment")
-def get_sentiment_details(input: inputtext):
-    
-    result = classifier(input)
-    print(result)  # Output will be a list: [{'label': 'POSITIVE', 'score': 0.999...}]
+def get_sentiment_details(input: InputText):  
+    text = input.text  # Extract the actual string from the Pydantic model
+
+    print(f"===== The type of the text is : {type(text)} =====")  # Debugging output
 
-    # Accessing the results:
+    result = classifier(text)  # Pass only the extracted string
     label = result[0]['label']
     score = result[0]['score']
-    print(f"Sentiment: {label}, Score: {score}")
-    
-    return label, score
-    
 
+    return {"sentiment": label, "score": score}
+    
 @app.post("/get_prediction_on_userinput")
 def run_pred_pipeline(input: PredictionInput):
 
@@ -112,11 +114,13 @@ def run_pred_pipeline(input: PredictionInput):
     ## Hardcoding for testing purposes ##
 
     temp_predictions_dict = generate_random_predictions()
+    sample_sim_attr = get_sample_similarity_attr()
     data_out = {
         "status" : "success",
         "data" : {
             "id": input.dict()['id'],
-            "predictions": temp_predictions_dict
+            "predictions": temp_predictions_dict,
+            "similarity_attr": sample_sim_attr
         #     "predictions": {
         #         "ASDA": {
         #             "Apr-25": 741.86,

helper.py

@@ -1,6 +1,181 @@
 import pandas as pd
 import numpy as np
 
+def get_sample_similarity_attr():
+    sample_sim = {
+        "GB1263": {
+            "sell_in_volume": 44426.88,
+            "similarity": 66.67,
+            "distribution": [
+                0,
+                0,
+                0,
+                0,
+                0,
+                0,
+                8,
+                9,
+                9,
+                9,
+                6,
+                5,
+                7,
+                25,
+                26,
+                27
+            ],
+            "week_date": [
+                "2024-05-13",
+                "2024-05-20",
+                "2024-05-27",
+                "2024-06-03",
+                "2024-06-10",
+                "2024-06-17",
+                "2024-06-24",
+                "2024-07-01",
+                "2024-07-08",
+                "2024-07-15",
+                "2024-07-22",
+                "2024-07-29",
+                "2024-08-05",
+                "2024-08-12",
+                "2024-08-19",
+                "2024-08-26"
+            ]
+        },
+        "GB1264": {
+            "sell_in_volume": 26840.97,
+            "similarity": 66.67,
+            "distribution": [
+                0,
+                0,
+                0,
+                0,
+                0,
+                0,
+                6,
+                8,
+                8,
+                8,
+                5,
+                4,
+                6,
+                25,
+                26,
+                27
+            ],
+            "week_date": [
+                "2024-05-13",
+                "2024-05-20",
+                "2024-05-27",
+                "2024-06-03",
+                "2024-06-10",
+                "2024-06-17",
+                "2024-06-24",
+                "2024-07-01",
+                "2024-07-08",
+                "2024-07-15",
+                "2024-07-22",
+                "2024-07-29",
+                "2024-08-05",
+                "2024-08-12",
+                "2024-08-19",
+                "2024-08-26"
+            ]
+        },
+        "GB1450": {
+            "sell_in_volume": 32346.0,
+            "similarity": 66.67,
+            "distribution": [
+                0,
+                0,
+                0,
+                0,
+                0,
+                0,
+                6,
+                8,
+                9,
+                8,
+                6,
+                4,
+                6,
+                25,
+                26,
+                27
+            ],
+            "week_date": [
+                "2024-05-13",
+                "2024-05-20",
+                "2024-05-27",
+                "2024-06-03",
+                "2024-06-10",
+                "2024-06-17",
+                "2024-06-24",
+                "2024-07-01",
+                "2024-07-08",
+                "2024-07-15",
+                "2024-07-22",
+                "2024-07-29",
+                "2024-08-05",
+                "2024-08-12",
+                "2024-08-19",
+                "2024-08-26"
+            ]
+        },
+        "GB1561": {
+            "sell_in_volume": 3265.92,
+            "similarity": 77.78,
+            "distribution": [
+                91,
+                34,
+                33,
+                33,
+                32,
+                33
+            ],
+            "week_date": [
+                "2024-02-12",
+                "2024-02-19",
+                "2024-02-26",
+                "2024-03-04",
+                "2024-03-11",
+                "2024-03-18"
+            ]
+        },
+        "GB1650": {
+            "sell_in_volume": 0.0,
+            "similarity": 77.78,
+            "distribution": [
+                38,
+                30,
+                24,
+                17,
+                14,
+                11,
+                9,
+                7,
+                7,
+                6,
+                5
+            ],
+            "week_date": [
+                "2024-02-12",
+                "2024-02-19",
+                "2024-02-26",
+                "2024-03-04",
+                "2024-03-11",
+                "2024-03-18",
+                "2024-03-25",
+                "2024-04-01",
+                "2024-04-08",
+                "2024-04-15",
+                "2024-04-22"
+            ]
+        }
+    }
+    return sample_sim
+
 def generate_random_predictions():
 
     # Number of rows and columns