init

.gitignore

@@ -0,0 +1,5 @@
+venv/
+env/
+.venv/
+.env/
+.env

main.py

@@ -0,0 +1,33 @@
+from typing import Union
+from src.utils import make_incredible_predictions
+from fastapi import FastAPI
+
+app = FastAPI()
+# /docs, page to see auto-generated API documentation
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World", "cohort": "2"}
+
+
+@app.get("/items/{item_id}")
+def read_item(item_id: int, q: Union[str, None] = None):
+    return {"item_id": item_id, "q": q}
+
+@app.get("/predict")
+def predict(age, salary, dependentsNumber, gender):
+    prediction = None
+    # prediction = model.predict(pd.DataFrame([age, salary, dependents_number, gender]))
+    return {"age":age, 
+            "salary":salary, 
+            "dependents_number":dependentsNumber, 
+            "gender":gender,"prediction":prediction}
+
+@app.post("/predict")
+def predict(age, salary, dependentsNumber, gender):
+    prediction = None
+    # prediction = model.predict(pd.DataFrame([age, salary, dependents_number, gender]))
+    return {"age":age, 
+            "salary":salary, 
+            "dependents_number":dependentsNumber, 
+            "gender":gender,"prediction":prediction}

main_sentiment.py

@@ -0,0 +1,58 @@
+# Imports
+import sys
+# sys.path.insert(0, '../src/')
+# sys.path.insert(0, '../src')
+# sys.path.insert(0, 'src/')
+# sys.path.insert(0, 'src')
+
+from typing import Union
+from src.utils import preprocess
+from fastapi import FastAPI
+from transformers import AutoModelForSequenceClassification,AutoTokenizer, AutoConfig
+import numpy as np
+#convert logits to probabilities
+from scipy.special import softmax
+
+# Config
+
+app = FastAPI()
+#/docs, page to see auto-generated API documentation
+
+#loading ML/DL components
+tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+model_path = f"Junr-syl/tweet_sentiments_analysis"
+config = AutoConfig.from_pretrained(model_path)
+config.id2label = {0: 'NEGATIVE', 1: 'NEUTRAL', 2: 'POSITIVE'}
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+# Endpoints
+@app.get("/")
+def read_root():
+    "Home endpoint"
+    return {"greeting": "Hello World..!", 
+            "cohort": "2",
+            }
+
+@app.post("/predict")
+def predict(text:str):
+    "prediction endpoint, classifying tweets"
+    
+    text = preprocess(text)
+
+    # PyTorch-based models
+    encoded_input = tokenizer(text, return_tensors='pt')
+    output = model(**encoded_input)
+    scores = output[0][0].detach().numpy()
+    scores = softmax(scores)
+
+    #Process scores
+    ranking = np.argsort(scores)
+    ranking = ranking[::-1]  
+    predicted_label = config.id2label[ranking[0]]
+    predicted_score = scores[ranking[0]]
+
+
+    return {"text":text,
+            "predicted_label":predicted_label,
+            "confidence_score":predicted_score
+            }

requirements.txt

@@ -0,0 +1,8 @@
+jupyter
+pandas
+scikit-learn
+fastapi[all]
+transformers
+torch
+seaborn
+plotly

src/main.py

@@ -0,0 +1,33 @@
+from typing import Union
+from src.utils import make_incredible_predictions
+from fastapi import FastAPI
+
+app = FastAPI()
+# /docs, page to see auto-generated API documentation
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World", "cohort": "2"}
+
+
+@app.get("/items/{item_id}")
+def read_item(item_id: int, q: Union[str, None] = None):
+    return {"item_id": item_id, "q": q}
+
+@app.get("/predict")
+def predict(age, salary, dependentsNumber, gender):
+    prediction = None
+    # prediction = model.predict(pd.DataFrame([age, salary, dependents_number, gender]))
+    return {"age":age, 
+            "salary":salary, 
+            "dependents_number":dependentsNumber, 
+            "gender":gender,"prediction":prediction}
+
+@app.post("/predict")
+def predict(age, salary, dependentsNumber, gender):
+    prediction = None
+    # prediction = model.predict(pd.DataFrame([age, salary, dependents_number, gender]))
+    return {"age":age, 
+            "salary":salary, 
+            "dependents_number":dependentsNumber, 
+            "gender":gender,"prediction":prediction}

src/main_sentiment.py

@@ -0,0 +1,58 @@
+# Imports
+import sys
+# sys.path.insert(0, '../src/')
+# sys.path.insert(0, '../src')
+# sys.path.insert(0, 'src/')
+# sys.path.insert(0, 'src')
+
+from typing import Union
+from src.utils import preprocess
+from fastapi import FastAPI
+from transformers import AutoModelForSequenceClassification,AutoTokenizer, AutoConfig
+import numpy as np
+#convert logits to probabilities
+from scipy.special import softmax
+
+# Config
+
+app = FastAPI()
+#/docs, page to see auto-generated API documentation
+
+#loading ML/DL components
+tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+model_path = f"Junr-syl/tweet_sentiments_analysis"
+config = AutoConfig.from_pretrained(model_path)
+config.id2label = {0: 'NEGATIVE', 1: 'NEUTRAL', 2: 'POSITIVE'}
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+# Endpoints
+@app.get("/")
+def read_root():
+    "Home endpoint"
+    return {"greeting": "Hello World..!", 
+            "cohort": "2",
+            }
+
+@app.post("/predict")
+def predict(text:str):
+    "prediction endpoint, classifying tweets"
+    
+    text = preprocess(text)
+
+    # PyTorch-based models
+    encoded_input = tokenizer(text, return_tensors='pt')
+    output = model(**encoded_input)
+    scores = output[0][0].detach().numpy()
+    scores = softmax(scores)
+
+    #Process scores
+    ranking = np.argsort(scores)
+    ranking = ranking[::-1]  
+    predicted_label = config.id2label[ranking[0]]
+    predicted_score = scores[ranking[0]]
+
+
+    return {"text":text,
+            "predicted_label":predicted_label,
+            "confidence_score":predicted_score
+            }

src/utils.py

@@ -0,0 +1,18 @@
+def make_incredible_predictions():
+    "This is the best function that have created"
+    pass
+
+def preprocess(text):
+    "preprocessing function of the input tweet"
+    
+    new_text = []#initiate an empty list 
+    #split text by space
+    for t in text.split(" "):
+        #set username to @user
+        t = '@user' if t.startswith('@') and len(t) > 1 else t  
+        #set tweet source to http
+        t = 'http' if t.startswith('http') else t 
+        #store text in the list
+        new_text.append(t)
+        #change text from list back to string
+    return " ".join(new_text) 

utils.py

@@ -0,0 +1,18 @@
+def make_incredible_predictions():
+    "This is the best function that have created"
+    pass
+
+def preprocess(text):
+    "preprocessing function of the input tweet"
+    
+    new_text = []#initiate an empty list 
+    #split text by space
+    for t in text.split(" "):
+        #set username to @user
+        t = '@user' if t.startswith('@') and len(t) > 1 else t  
+        #set tweet source to http
+        t = 'http' if t.startswith('http') else t 
+        #store text in the list
+        new_text.append(t)
+        #change text from list back to string
+    return " ".join(new_text)