From 59895f4b8a737d0a9af4922c4c75abc70a7f1436 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Sun, 13 Dec 2020 23:14:53 +0100
Subject: [PATCH] Remove imputation of values from part 2

---
 src/P1/processing.py    |  2 --
 src/P2/preprocessing.py | 16 ++-----------
 src/P2/processing.py    | 50 ++++-------------------------------------
 3 files changed, 6 insertions(+), 62 deletions(-)

diff --git a/src/P1/processing.py b/src/P1/processing.py
index 7edbbd0..2c59bce 100644
--- a/src/P1/processing.py
+++ b/src/P1/processing.py
@@ -89,7 +89,6 @@ def plot_confusion_matrix(results):
         axes[i].set_title(matrix.index[i])
     fig_title = "Confusion Matrix"
     suptitle(fig_title)
-    show()
     fig.savefig(f"docs/assets/{fig_title.replace(' ', '_').lower()}.png")
 
 
@@ -106,7 +105,6 @@ def plot_attributes_correlation(data, target):
         axes[i].set_title(transformed_data.columns[i])
     fig_title = "Attribute's correlation"
     suptitle(fig_title)
-    show()
     fig.savefig(f"docs/assets/{fig_title.replace(' ', '_').lower()}.png")
 
 
diff --git a/src/P2/preprocessing.py b/src/P2/preprocessing.py
index c68f8eb..31b518d 100644
--- a/src/P2/preprocessing.py
+++ b/src/P2/preprocessing.py
@@ -8,18 +8,6 @@ def replace_values(df):
     return df
 
 
-def process_na(df, action):
-    if action == "drop":
-        return df.dropna()
-    elif action == "fill":
-        return replace_values(df)
-    else:
-        print("Unknown action selected. The choices are: ")
-        print("fill: fills the na values with the mean")
-        print("drop: drops the na values")
-        exit()
-
-
 def filter_dataframe(df):
     relevant_columns = [
         "TOT_HERIDOS_LEVES",
@@ -39,8 +27,8 @@ def normalize_numerical_values(df):
     return df
 
 
-def parse_data(source, action):
+def parse_data(source):
     df = read_csv(filepath_or_buffer=source, na_values="?")
-    processed_df = process_na(df=df, action=action)
+    processed_df = df.dropna()
     normalized_df = normalize_numerical_values(df=processed_df)
     return normalized_df
diff --git a/src/P2/processing.py b/src/P2/processing.py
index 40e039b..aa0b0d5 100644
--- a/src/P2/processing.py
+++ b/src/P2/processing.py
@@ -3,7 +3,6 @@ from sys import argv
 
 from matplotlib.pyplot import *
 from pandas import DataFrame
-from seaborn import clustermap, set_style, set_theme, pairplot
 from sklearn.metrics import silhouette_score, calinski_harabasz_score
 from sklearn.cluster import KMeans, Birch, SpectralClustering, MeanShift, DBSCAN
 
@@ -49,47 +48,6 @@ def predict_data(data, model, cluster_number, results):
     return populated_results
 
 
-def plot_heatmap(results):
-    fig = figure(figsize=(20, 10))
-    results.reset_index()
-    matrix = results["prediction"]
-    print(matrix)
-    clustermap(
-        data=matrix,
-        cmap="mako",
-        metric="euclidean",
-        annot=True,
-    )
-    fig_title = "Heatmap"
-    title(fig_title)
-    show()
-    fig.savefig(f"docs/assets/{fig_title.replace(' ', '_').lower()}.png")
-
-
-def plot_scatter_plot(results):
-    fig = figure(figsize=(20, 10))
-    matrix = results.filter(items=["input", "prediction"])
-    pairplot(
-        data=results,
-        vars=matrix,
-        hue="prediction",
-        palette="Paired",
-        diag_kind="hist",
-    )
-    fig_title = "Scatter plot"
-    title(fig_title)
-    show()
-    fig.savefig(f"docs/assets/{fig_title.replace(' ', '_').lower()}.png")
-
-
-def show_results(results):
-    set_theme()
-    set_style("white")
-    plot_heatmap(results=results)
-    plot_scatter_plot(results=results)
-    print(results)
-
-
 def create_result_dataframes():
     results = DataFrame(
         columns=[
@@ -153,10 +111,10 @@ def usage():
 
 def main():
     models = ["kmeans", "birch", "spectral", "meanshift", "dbscan"]
-    if len(argv) != 4:
+    if len(argv) != 3:
         usage()
-    case, cluster_number = argv[2], int(argv[3])
-    data = parse_data(source="data/accidentes_2013.csv", action=str(argv[1]))
+    case, cluster_number = argv[1], int(argv[2])
+    data = parse_data(source="data/accidentes_2013.csv")
     individual_result, complete_results = create_result_dataframes()
     case_data = construct_case(df=data, choice=case)
     filtered_data = filter_dataframe(df=case_data)
@@ -171,7 +129,7 @@ def main():
             individual_result.append(model_results)
         )
     complete_results.set_index("model")
-    show_results(results=complete_results)
+    print(complete_results)
 
 
 if __name__ == "__main__":