zad5 model i skrypty

Dockerfile

@@ -11,12 +11,16 @@ RUN apt-get update && \
     unzip \
     && rm -rf /var/lib/apt/lists/*
 
-RUN pip3 install pandas scikit-learn requests kaggle
+RUN pip3 install pandas scikit-learn requests kaggle numpy
 
 WORKDIR /app
 
-COPY data_preparation_script.py /app/
+COPY model_creator.py /app/
+COPY use_model.py /app/
+COPY run_py_scripts.sh /app/
 
-RUN chmod +x data_preparation_script.py
 
-CMD ["python3", "data_preparation_script.py"]
+RUN chmod +x model_creator.py
+RUN chmod +x use_model.py
+
+CMD ["bash", "run_py_scripts.sh"]

model_creator.py

@@ -0,0 +1,127 @@
+import pandas as pd
+import os
+import numpy as np
+from kaggle.api.kaggle_api_extended import KaggleApi
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score
+from sklearn.preprocessing import StandardScaler
+from sklearn. preprocessing import LabelEncoder
+import pickle
+
+
+def download_dataset(dataset_address, destination_folder):
+    
+    api = KaggleApi()
+    api.authenticate()
+
+    api.dataset_download_files(dataset_address, path=destination_folder, unzip=True)
+
+
+def check_datasets_presence():
+    
+    dataset_1 = "Spotify_Dataset.csv"
+    dataset_2 = "spotify_songs.csv"
+    destination_folder = "datasets"
+
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+        print(f"Utworzono folder: {destination_folder}")
+    else:
+        print(f"Folder {destination_folder} już istnieje.")
+
+    if dataset_1 not in os.listdir(destination_folder):
+        download_dataset('gulczas/spotify-dataset', destination_folder)
+
+    if dataset_2 not in os.listdir(destination_folder):
+        download_dataset('joebeachcapital/30000-spotify-songs', destination_folder)
+
+
+def datasets_preparation():
+       df_1 = pd.read_csv("datasets/spotify_songs.csv")
+       df_2 = pd.read_csv("datasets/Spotify_Dataset.csv", sep=";")
+
+       df_1 = df_1.dropna()
+       df_2 = df_2.dropna()
+       df_2 = df_2.rename(columns={'Title': 'track_name'})
+
+       columns_to_remove_df_1 = ['track_id', 'track_album_id', 'track_album_name', 'track_album_release_date',
+                            'playlist_id', 'playlist_subgenre']
+       columns_to_remove_df_2 = ['Date','# of Artist', 'Artist (Ind.)', '# of Nationality',
+              'Nationality', 'Continent', 'Points (Total)',
+              'Points (Ind for each Artist/Nat)', 'id', 'Song URL']
+
+       df_1 = df_1.drop(columns=columns_to_remove_df_1)
+       df_2 = df_2.drop(columns=columns_to_remove_df_2)
+       df_1 = df_1.drop_duplicates(subset=['track_name'])
+       df_2 = df_2.drop_duplicates(subset=['track_name'])
+
+       le = LabelEncoder()
+
+       unique_names_df2 = df_2['track_name'].unique()
+       diff_df = df_1[~df_1['track_name'].isin(unique_names_df2)]
+       diff_df = diff_df.iloc[:10000]
+
+       #diff_df = pd.concat([diff_df, df_1.iloc[:20]], ignore_index=True)
+       diff_df['track_artist'] = le.fit_transform(diff_df.track_artist)
+       diff_df['playlist_name'] = le.fit_transform(diff_df.playlist_name)
+       diff_df['playlist_genre'] = le.fit_transform(diff_df.playlist_genre)
+
+       #df_1 = df_1.iloc[20:]
+       
+       if "docker_test_dataset.csv" not in os.listdir("datasets"):
+              diff_df.to_csv("datasets/docker_test_dataset.csv", index=False)
+
+       result_df = pd.merge(df_1, df_2, on='track_name', how='inner') 
+       result_df = result_df.drop_duplicates(subset=['track_name'])
+       columns_to_remove_result_df = ['Rank', 'Artists', 'Danceability', 'Energy', 'Loudness',
+       'Speechiness', 'Acousticness', 'Instrumentalness', 'Valence']
+       result_df = result_df.drop(columns=columns_to_remove_result_df)
+
+       result_df['track_artist'] = le.fit_transform(result_df.track_artist)
+       result_df['playlist_name'] = le.fit_transform(result_df.playlist_name)
+       result_df['playlist_genre'] = le.fit_transform(result_df.playlist_genre)
+       
+       return result_df
+
+
+check_datasets_presence()
+result_df = datasets_preparation()
+Y = result_df[['playlist_genre']]
+X = result_df.drop(columns='playlist_genre')
+X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.10, random_state=42)
+
+
+Y_train = np.ravel(Y_train)
+Y_test = np.ravel(Y_test)
+
+scaler = StandardScaler()
+numeric_columns = X_train.select_dtypes(include=['int', 'float']).columns
+X_train_scaled = scaler.fit_transform(X_train[numeric_columns])
+X_test_scaled = scaler.transform(X_test[numeric_columns])
+
+model = LogisticRegression(max_iter=1000)
+model.fit(X_train_scaled, Y_train)
+
+
+Y_pred = model.predict(X_test_scaled)
+
+accuracy = accuracy_score(Y_test, Y_pred)
+print("Accuracy:", accuracy)
+
+file_path = 'model.pkl'
+
+if os.path.exists(file_path):
+    os.remove(file_path)
+
+if file_path not in os.listdir("./"):
+    with open(file_path, 'wb') as file:
+        pickle.dump(model, file)
+
+print("Model został zapisany do pliku:", file_path)
+
+
+
+
+
+

model_predictions.txt

@@ -0,0 +1,3 @@
+Real:['edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm', 'edm'] 
+Predicted: ['pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop', 'pop']
+Accuracy:0.1521

run_py_scripts.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+python3 model_creator.py
+python3 use_model.py

use_model.py

@@ -0,0 +1,36 @@
+import pickle
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import accuracy_score
+
+np.set_printoptions(threshold=20)
+
+file_path = 'model.pkl'
+with open(file_path, 'rb') as file:
+    model = pickle.load(file)
+print("Model został wczytany z pliku:", file_path)
+
+test_df = pd.read_csv("datasets/docker_test_dataset.csv")
+
+Y_test = test_df[['playlist_genre']]
+X_test = test_df.drop(columns='playlist_genre')
+Y_test = np.ravel(Y_test)
+
+scaler = StandardScaler()
+numeric_columns = X_test.select_dtypes(include=['int', 'float']).columns
+X_test_scaled = scaler.fit_transform(X_test[numeric_columns])
+
+Y_pred = model.predict(X_test_scaled)
+
+with open('model_predictions.txt', 'w') as f:
+    pass
+
+with open('model_predictions.txt', 'a') as f:
+    labels_dict = {0: 'edm', 1 : 'latin', 2 : 'pop',  3 : 'r&b', 4 : 'rap', 5 :'rock'}
+    Y_test_labels = [labels_dict[number] for number in Y_test]
+    Y_pred_labels = [labels_dict[number] for number in Y_pred]
+    f.write("Real:" + str(Y_test_labels[:20])+ " \nPredicted: "+ str(Y_pred_labels[:20]))
+    accuracy = accuracy_score(Y_test, Y_pred)
+    f.write("\nAccuracy:" + str(accuracy))
+