566 lines
26 KiB
Plaintext
566 lines
26 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Laden der Rohdaten"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pickle\n",
|
|
"\n",
|
|
"# Laden der 'kirp' Liste aus der Pickle-Datei\n",
|
|
"with open('rick.pickle', 'rb') as f:\n",
|
|
" data_frame = pickle.load(f)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Aktiviere Cuda Support"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import torch\n",
|
|
"device = \"cpu\"\n",
|
|
"if torch.cuda.is_available():\n",
|
|
" print(\"CUDA is available on your system.\")\n",
|
|
" device = \"cuda\"\n",
|
|
"else:\n",
|
|
" print(\"CUDA is not available on your system.\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# PCA Klasse zu Reduktion der Dimensionen"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from torch.utils.data import Dataset\n",
|
|
"import torch\n",
|
|
"import pandas as pd\n",
|
|
"from sklearn.preprocessing import LabelEncoder\n",
|
|
"from sklearn.decomposition import PCA\n",
|
|
"from sklearn.preprocessing import StandardScaler\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from typing import List, Tuple, Dict\n",
|
|
"\n",
|
|
"\n",
|
|
"class GenomeDataset(Dataset):\n",
|
|
" \"\"\"\n",
|
|
" Eine benutzerdefinierte Dataset-Klasse, die für die Handhabung von Genomdaten konzipiert ist.\n",
|
|
" Diese Klasse wendet eine Principal Component Analysis (PCA) auf die Frequenzen der Genome an\n",
|
|
" und teilt den Datensatz in Trainings- und Validierungsteile auf.\n",
|
|
"\n",
|
|
" Attributes:\n",
|
|
" dataframe (pd.DataFrame): Ein Pandas DataFrame, der die initialen Daten enthält.\n",
|
|
" train_df (pd.DataFrame): Ein DataFrame, der den Trainingsdatensatz nach der Anwendung von PCA und der Aufteilung enthält.\n",
|
|
" val_df (pd.DataFrame): Ein DataFrame, der den Validierungsdatensatz nach der Anwendung von PCA und der Aufteilung enthält.\n",
|
|
"\n",
|
|
" Methods:\n",
|
|
" __init__(self, dataframe, n_pca_components=1034, train_size=0.8, split_random_state=42):\n",
|
|
" Konstruktor für die GenomeDataset Klasse.\n",
|
|
" _do_PCA(self, frequencies, n_components=1034):\n",
|
|
" Wendet PCA auf die gegebenen Frequenzen an.\n",
|
|
" _split_dataset(self, train_size=0.8, random_state=42):\n",
|
|
" Teilt den DataFrame in Trainings- und Validierungsdatensätze auf.\n",
|
|
" __getitem__(self, index):\n",
|
|
" Gibt ein Tupel aus transformierten Frequenzen und dem zugehörigen Krebstyp für einen gegebenen Index zurück.\n",
|
|
" __len__(self):\n",
|
|
" Gibt die Gesamtlänge der kombinierten Trainings- und Validierungsdatensätze zurück.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" def __init__(self, dataframe: pd.DataFrame, n_pca_components: int = 1034, train_size: float = 0.8, split_random_state: int = 42):\n",
|
|
" \"\"\"\n",
|
|
" Konstruktor für die GenomeDataset Klasse.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" dataframe (pd.DataFrame): Der DataFrame, der die Genome Frequenzen und Krebsarten enthält.\n",
|
|
" n_pca_components (int): Die Anzahl der PCA-Komponenten, auf die reduziert werden soll. Standardwert ist 1034.\n",
|
|
" train_size (float): Der Anteil der Daten, der als Trainingsdaten verwendet werden soll. Standardwert ist 0.8.\n",
|
|
" split_random_state (int): Der Zufalls-Saatwert, der für die Aufteilung des Datensatzes verwendet wird. Standardwert ist 42.\n",
|
|
" \"\"\"\n",
|
|
" self.dataframe = dataframe\n",
|
|
"\n",
|
|
" # Umwandlung der Krebsarten in numerische Werte\n",
|
|
" self.label_encoder = LabelEncoder()\n",
|
|
" self.dataframe['encoded_cancer_type'] = self.label_encoder.fit_transform(dataframe['cancer_type'])\n",
|
|
"\n",
|
|
" # Anwenden der PCA auf die Frequenzen\n",
|
|
" self.dataframe['pca_frequencies'] = self._do_PCA(self.dataframe['genome_frequencies'].tolist(), n_pca_components)\n",
|
|
"\n",
|
|
" # Teilen des DataFrame in Trainings- und Validierungsdatensatz\n",
|
|
" self._split_dataset(train_size=train_size, random_state=split_random_state)\n",
|
|
"\n",
|
|
" def transform_datapoint(self, datapoint: List[float]) -> List[float]:\n",
|
|
" \"\"\"\n",
|
|
" Transformiert einen einzelnen Datenpunkt durch Standardisierung und Anwendung der PCA.\n",
|
|
"\n",
|
|
" Diese Methode nimmt einen rohen Datenpunkt (eine Liste von Frequenzen), standardisiert ihn mit dem \n",
|
|
" zuvor angepassten Scaler und wendet dann die PCA-Transformation an, um ihn in den reduzierten \n",
|
|
" Feature-Raum zu überführen, der für das Training des Modells verwendet wurde.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" datapoint (List[float]): Ein roher Datenpunkt, bestehend aus einer Liste von Frequenzen.\n",
|
|
"\n",
|
|
" Returns:\n",
|
|
" List[float]: Der transformierte Datenpunkt, nach Anwendung der Standardisierung und der PCA.\n",
|
|
" \"\"\"\n",
|
|
" # Standardisierung des Datenpunkts\n",
|
|
" scaled_data_point = self.scaler.transform([datapoint])\n",
|
|
"\n",
|
|
" # PCA-Transformation des standardisierten Datenpunkts\n",
|
|
" pca_transformed_point = self.pca.transform(scaled_data_point)\n",
|
|
"\n",
|
|
" return pca_transformed_point.tolist()\n",
|
|
"\n",
|
|
" def _do_PCA(self, frequencies: List[List[float]], n_components: int = 1034) -> List[List[float]]:\n",
|
|
" \"\"\"\n",
|
|
" Wendet PCA auf die gegebenen Frequenzen an.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" frequencies (List[List[float]]): Die Liste der Frequenzen, auf die die PCA angewendet werden soll.\n",
|
|
" n_components (int): Die Anzahl der Komponenten für die PCA. Standardwert ist 1034.\n",
|
|
"\n",
|
|
" Returns:\n",
|
|
" List[List[float]]: Eine Liste von Listen, die die transformierten Frequenzen nach der PCA darstellt.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" # Standardisieren der Frequenzen\n",
|
|
" self.scaler = StandardScaler()\n",
|
|
" scaled_frequencies = self.scaler.fit_transform(frequencies)\n",
|
|
"\n",
|
|
" # PCA-Instanz erstellen und auf die gewünschte Anzahl von Komponenten reduzieren\n",
|
|
" self.pca = PCA(n_components=n_components)\n",
|
|
"\n",
|
|
" # PCA auf die Frequenzen anwenden\n",
|
|
" pca_result = self.pca.fit_transform(scaled_frequencies)\n",
|
|
"\n",
|
|
" return pca_result.tolist()\n",
|
|
"\n",
|
|
" def _split_dataset(self, train_size: float = 0.8, random_state: int = 42):\n",
|
|
" \"\"\"\n",
|
|
" Teilt den DataFrame in Trainings- und Validierungsdatensätze auf.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" train_size (float): Der Anteil der Daten, der als Trainingsdaten verwendet werden soll.\n",
|
|
" random_state (int): Der Zufalls-Saatwert, der für die Aufteilung des Datensatzes verwendet wird.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" class SplittedDataset(Dataset):\n",
|
|
" def __init__(self, dataframe):\n",
|
|
" self.dataframe = dataframe\n",
|
|
"\n",
|
|
" # Umwandlung der Genome Frequenzen in Tensoren\n",
|
|
" self.genome_frequencies = torch.tensor(dataframe['pca_frequencies'].tolist(), dtype=torch.float32)\n",
|
|
"\n",
|
|
" # Umwandlung der Krebsarten in numerische Werte\n",
|
|
" self.label_encoder = LabelEncoder()\n",
|
|
" self.cancer_types = torch.tensor(dataframe['encoded_cancer_type'].tolist(), dtype=torch.long)\n",
|
|
"\n",
|
|
" def __getitem__(self, index):\n",
|
|
" # Rückgabe eines Tupels aus Genome Frequenzen und dem entsprechenden Krebstyp\n",
|
|
" return self.genome_frequencies[index], self.cancer_types[index]\n",
|
|
"\n",
|
|
" def __len__(self):\n",
|
|
" return len(self.dataframe)\n",
|
|
"\n",
|
|
" # Teilen des DataFrame in Trainings- und Validierungsdatensatz\n",
|
|
" train_df, val_df = train_test_split(self.dataframe, train_size=train_size) #, random_state=random_state)\n",
|
|
" self.train_df = SplittedDataset(train_df)\n",
|
|
" self.val_df = SplittedDataset(val_df)\n",
|
|
"\n",
|
|
"\n",
|
|
" def __getitem__(self, index: int) -> Tuple[torch.Tensor, int]:\n",
|
|
" \"\"\"\n",
|
|
" Gibt ein Tupel aus transformierten Frequenzen und dem entsprechenden Krebstyp für einen gegebenen Index zurück.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" index (int): Der Index des zu abrufenden Datenelements.\n",
|
|
"\n",
|
|
" Returns:\n",
|
|
" Tuple[torch.Tensor, int]: Ein Tupel, bestehend aus einem Tensor der transformierten Frequenzen und dem zugehörigen Krebstyp.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" print(self.train_df.shape)\n",
|
|
" print(self.val_df.shape)\n",
|
|
" \n",
|
|
" if index < len(self.train_df):\n",
|
|
" row = self.train_df.iloc[index]\n",
|
|
" else:\n",
|
|
" row = self.val_df.iloc[len(self.train_df) - index]\n",
|
|
"\n",
|
|
" pca_frequencies_tensor = torch.tensor(row['pca_frequencies'], dtype=torch.float32)\n",
|
|
" cancer_type = row['encoded_cancer_type']\n",
|
|
"\n",
|
|
" return pca_frequencies_tensor, cancer_type\n",
|
|
"\n",
|
|
" def __len__(self) -> int:\n",
|
|
" \"\"\"\n",
|
|
" Gibt die Gesamtlänge der kombinierten Trainings- und Validierungsdatensätze zurück.\n",
|
|
"\n",
|
|
" Returns:\n",
|
|
" int: Die Länge der kombinierten Datensätze.\n",
|
|
" \"\"\"\n",
|
|
" \n",
|
|
" return len(self.train_df) + len(self.val_df)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Definition des neuronalen Netzes"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import torch\n",
|
|
"import torch.nn as nn\n",
|
|
"import torch.optim as optim\n",
|
|
"import torch.nn.functional as F\n",
|
|
"\n",
|
|
"class CancerClassifierNN(nn.Module):\n",
|
|
" \"\"\"\n",
|
|
" Eine benutzerdefinierte neuronale Netzwerkklassifikator-Klasse für die Krebsklassifikation.\n",
|
|
"\n",
|
|
" Diese Klasse definiert ein mehrschichtiges Perzeptron (MLP), das für die Klassifizierung von Krebsarten\n",
|
|
" anhand genetischer Frequenzdaten verwendet wird.\n",
|
|
"\n",
|
|
" Attributes:\n",
|
|
" fc1 (nn.Linear): Die erste lineare Schicht des Netzwerks.\n",
|
|
" fc2 (nn.Linear): Die zweite lineare Schicht des Netzwerks.\n",
|
|
" fc3 (nn.Linear): Die dritte lineare Schicht des Netzwerks.\n",
|
|
" fc4 (nn.Linear): Die Ausgabeschicht des Netzwerks.\n",
|
|
" dropout (nn.Dropout): Ein Dropout-Layer zur Vermeidung von Overfitting.\n",
|
|
"\n",
|
|
" Methods:\n",
|
|
" __init__(self, input_size: int, num_classes: int):\n",
|
|
" Konstruktor für die CancerClassifierNN Klasse.\n",
|
|
" forward(self, x: torch.Tensor) -> torch.Tensor:\n",
|
|
" Definiert den Vorwärtsdurchlauf des Netzwerks.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" def __init__(self, input_size: int, num_classes: int):\n",
|
|
" \"\"\"\n",
|
|
" Konstruktor für die CancerClassifierNN Klasse.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" input_size (int): Die Größe des Input-Features.\n",
|
|
" num_classes (int): Die Anzahl der Zielklassen.\n",
|
|
" \"\"\"\n",
|
|
" super(CancerClassifierNN, self).__init__()\n",
|
|
" # Definieren der Schichten\n",
|
|
" self.fc1 = nn.Linear(input_size, input_size) # Eingabeschicht\n",
|
|
" self.fc2 = nn.Linear(input_size, input_size//2) # Versteckte Schicht\n",
|
|
" self.fc3 = nn.Linear(input_size//2, input_size//4) # Weitere versteckte Schicht\n",
|
|
" self.fc4 = nn.Linear(input_size//4, num_classes) # Ausgabeschicht\n",
|
|
" self.dropout = nn.Dropout(p=0.5) # Dropout\n",
|
|
"\n",
|
|
" def forward(self, x: torch.Tensor) -> torch.Tensor:\n",
|
|
" \"\"\"\n",
|
|
" Definiert den Vorwärtsdurchlauf des Netzwerks.\n",
|
|
"\n",
|
|
" Parameters:\n",
|
|
" x (torch.Tensor): Der Input-Tensor für das Netzwerk.\n",
|
|
"\n",
|
|
" Returns:\n",
|
|
" torch.Tensor: Der Output-Tensor nach dem Durchlauf durch das Netzwerk.\n",
|
|
" \"\"\"\n",
|
|
" x = F.relu(self.fc1(x))\n",
|
|
" x = self.dropout(x)\n",
|
|
" x = F.relu(self.fc2(x))\n",
|
|
" x = self.dropout(x)\n",
|
|
" x = F.relu(self.fc3(x))\n",
|
|
" x = self.dropout(x)\n",
|
|
" x = torch.softmax(self.fc4(x), dim=1) # Oder F.log_softmax(x, dim=1) für Mehrklassenklassifikation\n",
|
|
" return x"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from torch.utils.data import DataLoader\n",
|
|
"import torch.optim as optim\n",
|
|
"from IPython.display import clear_output\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import numpy as np\n",
|
|
"import os\n",
|
|
"import pickle\n",
|
|
"\n",
|
|
"class ExperimentationalExperiments():\n",
|
|
"\n",
|
|
" def __init__(self) -> None:\n",
|
|
" self.results = None\n",
|
|
"\n",
|
|
" def run_single_experiment(self, train_loader: DataLoader, valid_loader: DataLoader, n_pca_components: int, n_epochs: int = 200, learning_rate: int = 0.0005, verbose: bool = True, experiment_num: int = None) -> Tuple:\n",
|
|
" if not isinstance(n_pca_components, int):\n",
|
|
" raise TypeError(\"n_pca_components must be an integers!\")\n",
|
|
"\n",
|
|
" model = CancerClassifierNN(input_size=n_pca_components, num_classes=3)\n",
|
|
" model.to(device=device)\n",
|
|
"\n",
|
|
" # Verlustfunktion\n",
|
|
" criterion = nn.CrossEntropyLoss()\n",
|
|
" # Optimierer\n",
|
|
" optimizer = optim.Adam(model.parameters(), lr=learning_rate)\n",
|
|
"\n",
|
|
" # Listen, um Verluste zu speichern\n",
|
|
" train_losses = []\n",
|
|
" valid_losses = []\n",
|
|
" train_accuracies = []\n",
|
|
" valid_accuracies = []\n",
|
|
"\n",
|
|
" for epoch in range(n_epochs):\n",
|
|
" model.train()\n",
|
|
" train_loss = 0.0\n",
|
|
" correct_predictions = 0\n",
|
|
" total_predictions = 0\n",
|
|
"\n",
|
|
" for i, (inputs, labels) in enumerate(train_loader):\n",
|
|
" inputs, labels = inputs.to(device), labels.to(device)\n",
|
|
" optimizer.zero_grad()\n",
|
|
" outputs = model(inputs)\n",
|
|
" loss = criterion(outputs, labels)\n",
|
|
" loss.backward()\n",
|
|
" optimizer.step()\n",
|
|
" train_loss += loss.item()\n",
|
|
"\n",
|
|
" # Berechnen der Genauigkeit\n",
|
|
" _, predicted = torch.max(outputs, 1)\n",
|
|
" correct_predictions += (predicted == labels).sum().item()\n",
|
|
" total_predictions += labels.size(0)\n",
|
|
"\n",
|
|
" # Durchschnittlicher Trainingsverlust und Genauigkeit\n",
|
|
" train_loss /= len(train_loader)\n",
|
|
" train_accuracy = correct_predictions / total_predictions\n",
|
|
" train_losses.append(train_loss)\n",
|
|
" train_accuracies.append(train_accuracy)\n",
|
|
"\n",
|
|
" # Validierungsverlust und Genauigkeit\n",
|
|
" model.eval()\n",
|
|
" valid_loss = 0.0\n",
|
|
" correct_predictions = 0\n",
|
|
" total_predictions = 0\n",
|
|
"\n",
|
|
" with torch.no_grad():\n",
|
|
" for inputs, labels in valid_loader:\n",
|
|
" inputs, labels = inputs.to(device), labels.to(device)\n",
|
|
" outputs = model(inputs)\n",
|
|
" loss = criterion(outputs, labels)\n",
|
|
" valid_loss += loss.item()\n",
|
|
"\n",
|
|
" # Berechnen der Genauigkeit\n",
|
|
" _, predicted = torch.max(outputs, 1)\n",
|
|
" correct_predictions += (predicted == labels).sum().item()\n",
|
|
" total_predictions += labels.size(0)\n",
|
|
"\n",
|
|
" # Durchschnittlicher Validierungsverlust und Genauigkeit\n",
|
|
" valid_loss /= len(valid_loader)\n",
|
|
" valid_accuracy = correct_predictions / total_predictions\n",
|
|
" valid_losses.append(valid_loss)\n",
|
|
" valid_accuracies.append(valid_accuracy)\n",
|
|
"\n",
|
|
" # Aktualisieren des Graphen\n",
|
|
" clear_output(wait=True)\n",
|
|
" fig, ax1 = plt.subplots()\n",
|
|
"\n",
|
|
" # Zeichnen der Verlustkurven\n",
|
|
" ax1.plot(train_losses, label='Trainingsverlust', color='r')\n",
|
|
" ax1.plot(valid_losses, label='Validierungsverlust', color='b')\n",
|
|
" ax1.set_xlabel('Epochen')\n",
|
|
" ax1.set_ylabel('Verlust', color='g')\n",
|
|
" ax1.tick_params(axis='y', labelcolor='g')\n",
|
|
"\n",
|
|
" # Zweite y-Achse für die Genauigkeit\n",
|
|
" ax2 = ax1.twinx()\n",
|
|
" ax2.plot(train_accuracies, label='Trainingsgenauigkeit', color='r', linestyle='dashed')\n",
|
|
" ax2.plot(valid_accuracies, label='Validierungsgenauigkeit', color='b', linestyle='dashed')\n",
|
|
" ax2.set_ylabel('Genauigkeit', color='g')\n",
|
|
" ax2.tick_params(axis='y', labelcolor='g')\n",
|
|
"\n",
|
|
" # Titel und Legende\n",
|
|
" plt.title(f'Experiment #{experiment_num}: Trainings- und Validierungsverlust und -genauigkeit über die Zeit mit \\n{n_pca_components}-Hauptkomponenten, Lernrate: {learning_rate}')\n",
|
|
" fig.tight_layout()\n",
|
|
"\n",
|
|
" # Legende außerhalb des Graphen\n",
|
|
" ax1.legend(loc='upper left', bbox_to_anchor=(1.15, 1))\n",
|
|
" ax2.legend(loc='upper left', bbox_to_anchor=(1.15, 0.85))\n",
|
|
"\n",
|
|
" # Fortschritt anzeigen, falls angegeben\n",
|
|
" if verbose:\n",
|
|
" print(f'Experiment #{experiment_num} mit {n_pca_components} PCA components: Epoch [{epoch+1}/{n_epochs}], Trainingsverlust: {train_loss:.4f}, Trainingsgenauigkeit: {train_accuracies[-1]:.4f}, Validierungsverlust: {valid_loss:.4f}, Validierungsgenauigkeit: {valid_accuracies[-1]:.4f}')\n",
|
|
"\n",
|
|
" # Plot speichern\n",
|
|
" name = str(experiment_num) + \".png\" if experiment_num is not None else \"single_experiment.png\"\n",
|
|
" if not os.path.exists(\"Experiments\"):\n",
|
|
" os.makedirs(\"Experiments\")\n",
|
|
" if not os.path.exists(f\"Experiments/{str(n_pca_components)}\"):\n",
|
|
" os.makedirs(f\"Experiments/{str(n_pca_components)}\")\n",
|
|
" plt.savefig(f\"Experiments/{str(n_pca_components)}/{name}\", bbox_inches='tight')\n",
|
|
"\n",
|
|
" return train_losses, valid_losses, train_accuracies, valid_accuracies\n",
|
|
"\n",
|
|
" def run_single_pca_experiment(self, train_loader: DataLoader, valid_loader: DataLoader, n_pca_components: int, n_experiments: int, n_epochs: int = 200, learning_rate: int = 0.0005, verbose: bool = True) -> List:\n",
|
|
" if not isinstance(n_pca_components, int):\n",
|
|
" raise TypeError(\"n_pca_components must be an integers!\")\n",
|
|
"\n",
|
|
" results = []\n",
|
|
"\n",
|
|
" for n in range(n_experiments):\n",
|
|
" res = self.run_single_experiment(train_loader, valid_loader, n_pca_components, n_epochs=n_epochs, learning_rate=learning_rate, verbose=verbose, experiment_num=n+1)\n",
|
|
" results.append(res)\n",
|
|
"\n",
|
|
" return results\n",
|
|
" \n",
|
|
"\n",
|
|
" def run(self, n_pca_components: List[int], n_experiments: int, n_epochs: int = 200, learning_rate: int = 0.0005, batch_size: int = 64, verbose: bool = True) -> Dict:\n",
|
|
" if not isinstance(n_pca_components, list):\n",
|
|
" raise TypeError(\"n_pca_components must be a list of integers!\")\n",
|
|
"\n",
|
|
" plt.ioff()\n",
|
|
" self.n_pca_components = n_pca_components\n",
|
|
"\n",
|
|
" results = {}\n",
|
|
"\n",
|
|
" for n_pca_comps in n_pca_components:\n",
|
|
" genome_dataset = GenomeDataset(data_frame, n_pca_components=n_pca_comps)\n",
|
|
" train_dataset = genome_dataset.train_df\n",
|
|
" valid_dataset = genome_dataset.val_df\n",
|
|
"\n",
|
|
" train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)\n",
|
|
" valid_loader = DataLoader(dataset=valid_dataset, batch_size=batch_size, shuffle=False)\n",
|
|
"\n",
|
|
" res = self.run_single_pca_experiment(train_loader, valid_loader, n_pca_comps, n_experiments, n_epochs=n_epochs, learning_rate=learning_rate, verbose=verbose)\n",
|
|
" results[str(n_pca_comps)] = res\n",
|
|
"\n",
|
|
" self.plot_and_save_results(res, n_pca_comps)\n",
|
|
"\n",
|
|
" self.results = results\n",
|
|
"\n",
|
|
" # Speichern der Daten in einer lokalen Datei\n",
|
|
" with open('Experiments/results.pickle', 'wb') as f:\n",
|
|
" pickle.dump(self.results, f)\n",
|
|
"\n",
|
|
" plt.ion()\n",
|
|
"\n",
|
|
" return results\n",
|
|
"\n",
|
|
" def plot_and_save_results(self, results: List[Tuple], n_pca_components: int) -> None:\n",
|
|
" # Mittelwerte und Standardabweichungen berechnen\n",
|
|
" train_losses, valid_losses, train_accuracies, valid_accuracies = zip(*results)\n",
|
|
"\n",
|
|
" train_losses = np.array(train_losses)\n",
|
|
" valid_losses = np.array(valid_losses)\n",
|
|
" train_accuracies = np.array(train_accuracies)\n",
|
|
" valid_accuracies = np.array(valid_accuracies)\n",
|
|
"\n",
|
|
" avg_train_losses = np.mean(train_losses, axis=0)\n",
|
|
" avg_valid_losses = np.mean(valid_losses, axis=0)\n",
|
|
" avg_train_acc = np.mean(train_accuracies, axis=0)\n",
|
|
" avg_valid_acc = np.mean(valid_accuracies, axis=0)\n",
|
|
"\n",
|
|
" std_train_losses = np.std(train_losses, axis=0)\n",
|
|
" std_valid_losses = np.std(valid_losses, axis=0)\n",
|
|
" std_train_acc = np.std(train_accuracies, axis=0)\n",
|
|
" std_valid_acc = np.std(valid_accuracies, axis=0)\n",
|
|
"\n",
|
|
" # Erstellen von Plots\n",
|
|
" epochs = range(1, len(avg_train_losses) + 1)\n",
|
|
"\n",
|
|
" # Plot für Verluste\n",
|
|
" plt.clf()\n",
|
|
" plt.plot(epochs, avg_train_losses, label='Mittlerer Trainingsverlust', color='r')\n",
|
|
" plt.fill_between(epochs, np.subtract(avg_train_losses, std_train_losses), np.add(avg_train_losses, std_train_losses), color='r', alpha=0.2)\n",
|
|
" plt.plot(epochs, avg_valid_losses, label='Mittlerer Validierungsverlust', color='b')\n",
|
|
" plt.fill_between(epochs, np.subtract(avg_valid_losses, std_valid_losses), np.add(avg_valid_losses, std_valid_losses), color='b', alpha=0.2)\n",
|
|
" plt.title(f'Mittelwert und Standardabweichung der Verluste für {n_pca_components} PCA-Komponenten')\n",
|
|
" plt.xlabel('Experiment Nummer')\n",
|
|
" plt.ylabel('Verlust')\n",
|
|
" plt.legend()\n",
|
|
" plt.savefig(f\"Experiments/{n_pca_components}/average_losses.png\", bbox_inches='tight')\n",
|
|
" plt.clf()\n",
|
|
"\n",
|
|
" # Plot für Genauigkeiten\n",
|
|
" plt.plot(epochs, avg_train_acc, label='Mittlere Trainingsgenauigkeit', color='r')\n",
|
|
" plt.fill_between(epochs, np.subtract(avg_train_acc, std_train_acc), np.add(avg_train_acc, std_train_acc), color='r', alpha=0.2)\n",
|
|
" plt.plot(epochs, avg_valid_acc, label='Mittlere Validierungsgenauigkeit', color='b')\n",
|
|
" plt.fill_between(epochs, np.subtract(avg_valid_acc, std_valid_acc), np.add(avg_valid_acc, std_valid_acc), color='b', alpha=0.2)\n",
|
|
" plt.title(f'Mittelwert und Standardabweichung der Genauigkeiten für {n_pca_components} PCA-Komponenten')\n",
|
|
" plt.xlabel('Experiment Nummer')\n",
|
|
" plt.ylabel('Genauigkeit')\n",
|
|
" plt.legend()\n",
|
|
" plt.savefig(f\"Experiments/{n_pca_components}/average_accuracies.png\", bbox_inches='tight')\n",
|
|
" plt.clf()\n",
|
|
"\n",
|
|
" "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"e = ExperimentationalExperiments()\n",
|
|
"results = e.run([1024, 512, 256, 128, 64, 32, 16], 10, n_epochs=500)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "rl",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.8.18"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|