Add processing module

docs/Summary.org

@@ -0,0 +1,26 @@
+#+TITLE: Práctica 3
+#+SUBTITLE: Inteligencia de Negocio
+#+AUTHOR: Amin Kasrou Aouam
+#+DATE: 2021-01-01
+#+PANDOC_OPTIONS: template:~/.pandoc/templates/eisvogel.latex
+#+PANDOC_OPTIONS: listings:t
+#+PANDOC_OPTIONS: toc:t
+#+PANDOC_METADATA: lang=es
+#+PANDOC_METADATA: titlepage:t
+#+PANDOC_METADATA: listings-no-page-break:t
+#+PANDOC_METADATA: toc-own-page:t
+#+PANDOC_METADATA: table-use-row-colors:t
+#+PANDOC_METADATA: logo:/home/coolneng/Photos/Logos/UGR.png
+* Práctica 3
+** Introducción
+
+En esta práctica, resolveremos un problema de clasificación multiclase, en concreto, trataremos de predecir la categoría de precio de una serie de coches
+
+** Preprocesamiento de datos
+*** Valores nulos
+*** Valores no numéricos
+*** Balanceo de clases
+** Elección de algoritmo
+** Configuración del algoritmo
+** Resultados obtenidos
+** Análisis de resultados

src/preprocessing.py

@@ -1,6 +1,7 @@
 from pandas import DataFrame, read_csv
 from sklearn.preprocessing import LabelEncoder
 from sklearn.model_selection import KFold
+from imblearn.combine import SMOTETomek
 
 
 def construct_dataframes(train, test):
@@ -12,19 +13,20 @@ def construct_dataframes(train, test):
     return df_list
 
 
-def drop_null_values(df_list):
-    for df in df_list:
-        df.dropna(inplace=True)
-        df.drop(columns="Tipo_marchas", inplace=True)
-    return df_list
-
-
 def rename_columns(df_list) -> DataFrame:
     for df in df_list:
         df.columns = df.columns.str.lower()
     return df_list
 
 
+def drop_null_values(df_list):
+    for df in df_list:
+        df.dropna(inplace=True)
+        df.drop(columns="tipo_marchas", inplace=True)
+        df["descuento"].fillna(0)
+    return df_list
+
+
 def trim_column_names(df_list) -> DataFrame:
     columns = ["consumo", "motor_CC", "potencia"]
     for df in df_list:
@@ -55,6 +57,26 @@ def encode_columns(df_list):
     return df_list
 
 
+def split_data_target(df, dataset):
+    if dataset == "data":
+        df.drop(columns="id", inplace=True)
+        data = df.drop(columns=["precio_cat"])
+        target = df["precio_cat"]
+    else:
+        data = df.drop(columns=["id"])
+        target = df["id"]
+    return data, target
+
+
+def balance_training_data(df):
+    smote_tomek = SMOTETomek(random_state=42)
+    data, target = split_data_target(df=df, dataset="data")
+    balanced_data, balanced_target = smote_tomek.fit_resample(data, target)
+    balanced_data_df = DataFrame(balanced_data, columns=data.columns)
+    balanced_target_df = DataFrame(balanced_target, columns=target.columns)
+    return balanced_data_df, balanced_target_df
+
+
 def split_k_sets(df):
     k_fold = KFold(shuffle=True, random_state=42)
     return k_fold.split(df)
@@ -66,4 +88,6 @@ def parse_data(train, test):
     processed_df_list = drop_null_values(renamed_df_list)
     numeric_df_list = trim_column_names(processed_df_list)
     encoded_df_list = encode_columns(numeric_df_list)
-    return encoded_df_list
+    train_data, train_target = balance_training_data(encoded_df_list[0])
+    test_data, test_ids = split_data_target(encoded_df_list[1], dataset="test")
+    return train_data, train_target, test_data, test_ids

src/processing.py

@@ -0,0 +1,51 @@
+from numpy import mean
+from pandas import DataFrame
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import cross_val_score
+from sklearn.ensemble import GradientBoostingClassifier
+
+from preprocessing import parse_data, split_k_sets
+
+
+def predict_data(train_data, train_target, test_data, test_ids):
+    model = GradientBoostingClassifier(random_state=42)
+    accuracy_scores = []
+    for train_index, test_index in split_k_sets(train_data):
+        model.fit(train_data.iloc[train_index], train_target.iloc[train_index])
+        prediction = model.predict(train_data.iloc[test_index])
+        accuracy_scores.append(
+            accuracy_score(train_target.iloc[test_index], prediction)
+        )
+    cv_score = cross_val_score(model, train_data, train_target)
+    evaluate_performance(
+        accuracy=mean(accuracy_scores),
+        cv_score=mean(cv_score),
+    )
+    predictions = model.predict(test_data)
+    export_results(ids=test_ids, prediction=predictions)
+
+
+def evaluate_performance(accuracy, cv_score):
+    print("Accuracy Score: " + str(accuracy))
+    print("Cross validation score: " + str(cv_score))
+
+
+def export_results(ids, prediction):
+    result_df = DataFrame({"id": ids, "Precio_cat": prediction})
+    result_df.to_csv(path_or_buf="data/results.csv", index=False)
+
+
+def main():
+    train_data, train_target, test_data, test_ids = parse_data(
+        train="data/train.csv", test="data/test.csv"
+    )
+    predict_data(
+        train_data=train_data,
+        train_target=train_target,
+        test_data=test_data,
+        test_ids=test_ids,
+    )
+
+
+if __name__ == "__main__":
+    main()