ultima versao

app.py

@@ -66,22 +66,32 @@ def calculaTFIDFSVM(titulo, descricao):
     context = titulo + descricao
     d = {"context": [context]}
     df = pd.DataFrame(data=d, columns=["context"])
-    vectorizer = load("model/vectorizer_tfidf.pkl")
+    vectorizer = load("model/vectorizer_tfidfsvm.pkl")
+    X = vectorizer.transform(df["context"])
+    story_points = model.predict(X)
+    return story_points
+
+def calculaTFIDFLinear(titulo, descricao):
+    model = load("model/model_tawos_aloy_tfidflinear.pkl")
+    context = titulo + descricao
+    d = {"context": [context]}
+    df = pd.DataFrame(data=d, columns=["context"])
+    vectorizer = load("model/vectorizer_tfidflinear.pkl")
     X = vectorizer.transform(df["context"])
-    
     story_points = model.predict(X)
     return story_points
 
 def calcula(titulo, descricao):
-    return calcula_MbR(titulo, descricao), calcula_neosp(titulo, descricao), calculaTFIDFSVM(titulo, descricao)
+    return calcula_MbR(titulo, descricao), calcula_neosp(titulo, descricao), calculaTFIDFSVM(titulo, descricao), calculaTFIDFLinear(titulo, descricao)
 
 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 MbR"),
                              gr.Textbox(label="Story Points Estimado NEOSP-SVR"),
-                             gr.Textbox(label="Story Points Estimado TFIDF-SVR")],
-                    title="Agile Task Story Point Estimator - TAWOS - Alloy",
+                             gr.Textbox(label="Story Points Estimado TFIDF-SVR"),
+                             gr.Textbox(label="Story Points Estimado TFIDF-Linear")],
+                    title="Agile Task Story Point Estimator",
                     examples=[[titulo1, descricao1], [titulo2, descricao2], [titulo3, descricao3], [titulo4, descricao4], [titulo5, descricao5]]
                     )
 

gerar_modelos/gerar_modelos_tfidflinear.py

@@ -0,0 +1,36 @@
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LinearRegression
+import pandas as pd
+import nltk
+from nltk.corpus import stopwords
+from joblib import dump
+
+# Carregando os dados
+df = pd.read_csv("dataset/ALOY_deep-se.csv")
+
+# Tirando os 5 Primeiros
+df = df.iloc[5:df.shape[0]]
+
+# Criando a coluna contexto = titulo + descricao
+df["context"] = df["title"] + df["description"]
+
+# Pré-processamento
+nltk.download('stopwords')
+stop = stopwords.words('english')
+df['context'] = df['context'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stop)]))
+
+# Extração de features
+vectorizer = TfidfVectorizer()
+X = vectorizer.fit_transform(df["context"])
+y = df["storypoint"]
+
+# Modelos
+model = LinearRegression()
+model.fit(X, y)
+
+dump(vectorizer, "model/vectorizer_tfidflinear.pkl")
+dump(model, "model/model_tawos_aloy_tfidflinear.pkl")
+
+
+
+  

gerar_modelos/gerar_modelos_tfidfsvm.py

@@ -28,7 +28,7 @@ y = df["storypoint"]
 model = svm.SVR()
 model.fit(X, y)
 
-dump(vectorizer, "model/vectorizer_tfidf.pkl")
+dump(vectorizer, "model/vectorizer_tfidfsvm.pkl")
 dump(model, "model/model_tawos_aloy_tfidfsvm.pkl")
 
 

gerar_modelos/temp.py

@@ -1,13 +0,0 @@
-from sklearn.dummy import DummyRegressor
-import pandas as pd
-from nltk.corpus import stopwords
-from joblib import dump
-
-# carregando os dados
-df = pd.read_csv("dataset/ALOY_deep-se.csv")
-
-print(df.shape)
-
-df = df.iloc[1:df.shape[0]]
-
-print(df.shape)

model/model_tawos_aloy_tfidflinear.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303f877f464839fa0f901c430ac518c5faccad753e8c59dd9c6e80a613c70bb6
+size 28056

model/{vectorizer_tfidf.pkl → vectorizer_tfidflinear.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b41fefa5560f7e858462dad642e89e5274da92e03ab69291e18127a835fad5f
+oid sha256:81af13f0ea1e088c522690d9d75968ad1a9307443066e6cc1af99cb2c22f109f
 size 102859

model/vectorizer_tfidfsvm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81af13f0ea1e088c522690d9d75968ad1a9307443066e6cc1af99cb2c22f109f
+size 102859