Remove type hints and the rename_model function

src/P1/processing.py

@@ -29,8 +29,9 @@ def choose_model(model):
 
 
 def predict_data(data, target, model, results):
-    model = choose_model(model)
-    if model == "knn":
+    model_name = model
+    model = choose_model(model=model)
+    if model_name == "knn":
         data = scale(data)
     confusion_matrices, auc, fpr, tpr = [], [], [], []
     for train_index, test_index in split_k_sets(data):
@@ -43,7 +44,7 @@ def predict_data(data, target, model, results):
         tpr.append(tpr_item)
     populated_results = populate_results(
         df=results,
-        model=model,
+        model=model_name,
         fpr=mean(fpr, axis=0),
         tpr=mean(tpr, axis=0),
         auc=mean(auc),
@@ -122,27 +123,13 @@ def create_result_dataframes():
 
 
 def populate_results(df, model, fpr, tpr, auc, confusion_matrix):
-    renamed_model = rename_model(model=f"{model}")
     columns = ["model", "fpr", "tpr", "auc", "confusion_matrix"]
-    values = [renamed_model, fpr, tpr, auc, confusion_matrix]
+    values = [model, fpr, tpr, auc, confusion_matrix]
     dictionary = dict(zip(columns, values))
     populated_df = df.append(dictionary, ignore_index=True)
     return populated_df
 
 
-def rename_model(model):
-    short_name = ["gnb", "svc", "knn", "tree", "neuralnet"]
-    models = [
-        "GaussianNB()",
-        "LinearSVC(random_state=42)",
-        "KNeighborsClassifier(n_neighbors=10)",
-        "DecisionTreeClassifier(random_state=42)",
-        "MLPClassifier(hidden_layer_sizes=10)",
-    ]
-    mapping = dict(zip(models, short_name))
-    return mapping[model]
-
-
 def transform_dataframe(data, target):
     joined_df = data.join(target)
     binned_df = joined_df.copy()

src/P2/preprocessing.py

@@ -2,13 +2,13 @@ from pandas import DataFrame, read_csv
 from sklearn.preprocessing import normalize
 
 
-def replace_values(df) -> DataFrame:
+def replace_values(df):
     for column in df.columns:
         df[column].fillna(value=df[column].mean(), inplace=True)
     return df
 
 
-def process_na(df, action) -> DataFrame:
+def process_na(df, action):
     if action == "drop":
         return df.dropna()
     elif action == "fill":
@@ -20,7 +20,7 @@ def process_na(df, action) -> DataFrame:
         exit()
 
 
-def filter_dataframe(df) -> DataFrame:
+def filter_dataframe(df):
     relevant_columns = [
         "HORA",
         "DIASEMANA",
@@ -38,18 +38,7 @@ def filter_dataframe(df) -> DataFrame:
     return filtered_df
 
 
-def choose_numerical_values(df):
-    cols = [
-        "TOT_HERIDOS_LEVES",
-        "TOT_HERIDOS_GRAVES",
-        "TOT_VEHICULOS_IMPLICADOS",
-        "TOT_MUERTOS",
-    ]
-    filtered_df = df.filter(items=cols)
-    return filtered_df
-
-
-def normalize_numerical_values(df) -> DataFrame:
+def normalize_numerical_values(df):
     cols = [
         "TOT_HERIDOS_LEVES",
         "TOT_HERIDOS_GRAVES",
@@ -63,7 +52,7 @@ def normalize_numerical_values(df) -> DataFrame:
     return df
 
 
-def parse_data(source, action) -> DataFrame:
+def parse_data(source, action):
     df = read_csv(filepath_or_buffer=source, na_values="?")
     processed_df = process_na(df=df, action=action)
     filtered_df = filter_dataframe(df=processed_df)

src/P2/processing.py

@@ -1,5 +1,4 @@
 import time
-from typing import Union
 from sys import argv
 
 from matplotlib.pyplot import *
@@ -8,12 +7,10 @@ from seaborn import heatmap, set_style, set_theme, pairplot
 from sklearn.metrics import silhouette_score, calinski_harabasz_score
 from sklearn.cluster import KMeans, Birch, AffinityPropagation, MeanShift, DBSCAN
 
-from preprocessing import parse_data, choose_numerical_values
+from preprocessing import parse_data
 
 
-def choose_model(
-    model,
-) -> Union[KMeans, Birch, AffinityPropagation, MeanShift, DBSCAN, None]:
+def choose_model(model):
     if model == "kmeans":
         return KMeans(random_state=42)
     elif model == "birch":
@@ -26,22 +23,22 @@ def choose_model(
         return DBSCAN()
 
 
-def predict_data(data, model, results, sample) -> DataFrame:
+def predict_data(data, model, results, sample):
+    model_name = model
     model = choose_model(model)
     start_time = time.time()
-    numerical_data = choose_numerical_values(df=data)
-    prediction = model.fit_predict(numerical_data)
+    prediction = model.fit_predict(data)
     execution_time = time.time() - start_time
-    calinski = calinski_harabasz_score(X=numerical_data, labels=prediction)
+    calinski = calinski_harabasz_score(X=data, labels=prediction)
     silhouette = silhouette_score(
-        X=numerical_data,
+        X=data,
         labels=prediction,
         metric="euclidean",
         sample_size=sample,
     )
     populated_results = populate_results(
         df=results,
-        model=model,
+        model=model_name,
         prediction=prediction,
         clusters=len(prediction),
         calinski=calinski,
@@ -110,10 +107,7 @@ def create_result_dataframes():
     return indexed_results, indexed_results
 
 
-def populate_results(
-    df, model, clusters, prediction, calinski, silhouette, time
-) -> DataFrame:
-    renamed_model = rename_model(model=f"{model}")
+def populate_results(df, model, clusters, prediction, calinski, silhouette, time):
     columns = [
         "model",
         "clusters",
@@ -122,25 +116,12 @@ def populate_results(
         "calinski-harabasz",
         "time",
     ]
-    values = [renamed_model, clusters, prediction, silhouette, calinski, time]
+    values = [model, clusters, prediction, silhouette, calinski, time]
     dictionary = dict(zip(columns, values))
     populated_df = df.append(dictionary, ignore_index=True)
     return populated_df
 
 
-def rename_model(model) -> str:
-    short_name = ["kmeans", "birch", "affinity", "meanshift", "dbscan"]
-    models = [
-        "KMeans(random_state=42)",
-        "Birch()",
-        "AffinityPropagation(random_state=42)",
-        "MeanShift()",
-        "DBSCAN()",
-    ]
-    mapping = dict(zip(models, short_name))
-    return mapping[model]
-
-
 def construct_case(df, choice):
     cases = {
         "case1": df.loc[(df["LUMINOSIDAD"].str.contains("NOCHE"))],