ultima versao

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-import pickle
+from joblib import dump, load
 
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.feature_selection import SelectKBest
@@ -10,35 +10,47 @@ import pandas as pd
 titulo = """CLONE - Studio Dashboard: "default" and "Default Project" does not give clear information about Alloy and Project unless description is read."""
 descricao = """Steps To Reproduce: 1. On dashboard on studio 3.0, navigate to Develop tab. 2. Notice "default" and "Default Project" & "two-tabbed" and "Tabbed Application" names. Actual: User does not get clear information from names that one is alloy project and another one is Titanium project unless he reads the description below. Expected: Naming convention or icon corresponding must suggest type"""
 
-
 titulo1 = """Ti.UI.Picker has no collection binding"""
 descricao1 = """h3. original discussion http://developer.appcelerator.com/question/145992/databinding-on-picker h3. problem Collection binding is not implemented for Ti.UI.Picker as it is for Ti.UI.TableView and other generic Titaniums views (View, Window, ScrollView, etc...). h3. solution Support collection binding on Ti.UI.Picker just as it is on TableView. It will need special handling as the Ti.UI.Picker requires custom parsing for columns and rows. Something like this should be how it would work for devs: {code:xml} <Alloy> <Collection src="book" /> <Window class="container"> <Picker dataCollection="book"> <PickerRow title="{title}" /> </Picker> </Window> </Alloy> {code}"""
 
-
-def calcula(titulo, descricao):
-    with open("model/model_tawos_aloy.pkl", "rb") as file:
-        model = pickle.load(file)
-
+def calcula_MbR(titulo, descricao):
     context = titulo + descricao
     d = {"context": [context]}
     df = pd.DataFrame(data=d, columns=["context"])
+    model = load("model/model_tawos_aloy_mbr.pkl")
+    story_points_MbR = model.predict(df["context"])
+    return story_points_MbR
 
+def calcula_sent(titulo, descricao):
+    model = load("model/model_tawos_aloy_mbr.pkl")
+    context = titulo + descricao
+    d = {"context": [context]}
+    df = pd.DataFrame(data=d, columns=["context"])
+    story_points = model.predict(df["context"])
+    return story_points
+    
+def calculaTFIDF(titulo, descricao):
+    model = load("model/model_tawos_aloy.pkl")
+    context = titulo + descricao
+    d = {"context": [context]}
+    df = pd.DataFrame(data=d, columns=["context"])
     vectorizer = TfidfVectorizer()
     X = vectorizer.fit_transform(df["context"])
-
     #X_new = SelectKBest(f_classif, k=50).fit_transfor(X)
-    
     story_points = model.predict(X)
-
     return story_points
 
+def calcula(titulo, descricao):
+    return 0, calcula_MbR(titulo, descricao), 0
+
 demo = gr.Interface(fn=calcula, 
                     inputs=[gr.Textbox(placeholder="Título", label="Título"), 
                             gr.Textbox(lines=10, placeholder="Descrição", label="Descrição")], 
-                    outputs=[gr.Textbox(label="Story Points Estimado")],
+                    outputs=[gr.Textbox(label="Story Points Estimado MbR"),
+                             gr.Textbox(label="Story Points Estimado NEOSP"),
+                             gr.Textbox(label="Story Points Estimado TFIDF-SVM")],
                     title="Agile Task Story Point Estimator - TAWOS - Alloy",
                     examples=[[titulo, descricao]]
                     )
 
-
 demo.launch() 

model/model_tawos_aloy_mbr.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78370715400e421619c699d1ac6b36b751eb479eaba46f024d70f12cc90fbfa2
+size 383