Merge pull request #19 from denBruneBarone/format_corrections

REFACTOR: Made small format changes/corrections across several files.

README.md

@@ -63,6 +63,6 @@ All documentation can be found on Overleaf
 
 
 ### Contact Info
-Please call 30246017
+In order to contact an author, please feel free to send an e-mail or via GitHub.
 
 Available all hours.

data_processing/data_cleansing/functions.py

@@ -2,4 +2,4 @@
 
 
 def read_csv(file_path):
- return pd.read_csv(file_path)
+ return pd.read_csv(file_path)

data_processing/energy_consumption/read_energy_consumption.py

@@ -1,8 +1,6 @@
 import pandas as pd
 import matplotlib.pyplot as plt
-
-from data_processing.energy_consumption import datapoints_summation, trapeziod_integration
-from data_processing.energy_consumption.trapeziod_integration import trapezoidal_integration
+from data_processing.energy_consumption import trapeziod_integration
 
 
 def read_csv():
@@ -14,14 +12,16 @@ def read_csv():
 def plot_connected_graph(data_x, data_y, label, color, linestyle='-'):
  plt.plot(data_x, data_y, linestyle, color=color, marker='o', label=label)
 
+
 def plot_stacked_chart(data_summing, data_integrated):
  plt.figure(figsize=(50, 30))
 
  # Plot connected graph for data_summing
  plt.plot(list(data_summing.keys()), list(data_summing.values()), color='blue', marker='o', label='Data Summing')
 
  # Plot connected graph for data_integrated
- plt.plot(list(data_integrated.keys()), list(data_integrated.values()), color='orange', marker='o', label='Data Integrated')
+ plt.plot(list(data_integrated.keys()), list(data_integrated.values()), color='orange', marker='o',
+ label='Data Integrated')
 
  # Stacked chart
  for flight in data_summing.keys():

data_processing/energy_consumption/trapeziod_integration.py

@@ -1,5 +1,4 @@
 import numpy as np
-import pandas as pd
 from scipy.interpolate import interp1d
 
 
@@ -39,9 +38,6 @@ def integrate_flight_data(df):
  return flight_energy
 
 
-
-
-# TODO: Caasper fix this. Lige nu finder jeg ikke integralet ved interpolation. Jeg laver den udregning, som du brugte i starten.
 def add_power_to_df(df):
  df['power_consumption'] = df['battery_voltage'] * df['battery_current']
  df = df.sort_values(by='time')
@@ -65,7 +61,8 @@ def integrate_specific_flight_data(data):
 
 
 def integrate_each_row_specific_flight_data(data):
- """Integrate power consumption for flight 1 between each consecutive pair of rows and add integrated power to DataFrame."""
+ """Integrate power consumption for flight 1 between each consecutive pair of rows
+ and add integrated power to DataFrame."""
  flight_data = data[data['flight'] == 1] # Filter data for flight 1
  time_points = flight_data['time'].values
  power_values = calculate_power(flight_data)
@@ -98,4 +95,3 @@ def add_cumulative_column(data):
  """Add a cumulative sum column to the flight data."""
  data['cumulative'] = data['integrated_power'].cumsum()
  return data
-

machine_learning/grid_search.py

@@ -2,37 +2,35 @@
 from sklearn.model_selection import GridSearchCV, KFold
 from sklearn.tree import DecisionTreeRegressor
 from machine_learning.config import GridSearchConfig
-from machine_learning.prepare_for_training import organize_data
+from machine_learning.prepare_for_training import format_data
+
 
 def grid_search(array_of_df):
  # n_splits: number of subsets,
  # splits the train-val data into n_splits number of subsets for cross validation
  decisionTree = DecisionTreeRegressor()
- cv = KFold(n_splits = 5, shuffle = True, random_state = 42)
+ cv = KFold(n_splits=5, shuffle=True, random_state=42)
 
- grid_search = GridSearchCV(estimator = decisionTree, param_grid = GridSearchConfig.param_grid,
- cv = cv, scoring = 'friedman_mse')
+ grid_search = GridSearchCV(estimator=decisionTree, param_grid=GridSearchConfig.param_grid,
+ cv=cv, scoring='friedman_mse')
 
- flight_dict_list = organize_data(array_of_df)
+ flight_dict_list = format_data(array_of_df)
 
  # Extract features and target variable from flight_dict_list
- X_train_list = [flight['data'] for flight in flight_dict_list]
+ x_train_list = [flight['data'] for flight in flight_dict_list]
  y_train_list = [flight['power'] for flight in flight_dict_list]
 
  # Convert lists of DataFrames/Series into a single DataFrame and Series
- X_train = pd.concat(X_train_list, ignore_index=True)
+ x_train = pd.concat(x_train_list, ignore_index=True)
  y_train = pd.concat(y_train_list, ignore_index=True)
 
  # Perform grid search
- grid_search.fit(X_train, y_train)
+ grid_search.fit(x_train, y_train)
 
  best_params = grid_search.best_params_
  best_score = grid_search.best_score_
 
  best_regressor = DecisionTreeRegressor(**best_params)
- best_regressor.fit(X_train, y_train)
+ best_regressor.fit(x_train, y_train)
 
  return best_params, best_score, best_regressor
-
-
-

machine_learning/pre_processing.py

@@ -14,12 +14,11 @@ def extract_flights(df):
 
 def split_data(df, train_size=0.8, random_state=42):
  flights_list = extract_flights(df)
- train_data, test_data = train_test_split(flights_list, test_size=1-train_size, random_state=random_state)
+ train_data, test_data = train_test_split(flights_list, test_size=1 - train_size, random_state=random_state)
  return train_data, test_data
 
 
 def pre_process_and_split_data(file_path):
  df = load_data(file_path)
  train_data, test_data = split_data(df)
  return train_data, test_data
-

machine_learning/prepare_for_training.py

@@ -1,5 +1,3 @@
-import numpy as np
-from torch.utils.data import Dataset
 from data_processing.energy_consumption.trapeziod_integration import add_power_to_df
 from sklearn.preprocessing import StandardScaler
 import pandas as pd

machine_learning/training.py

@@ -65,18 +65,16 @@ def training_and_evaluating(train_data, test_data):
  # Calculate RMSE on the original cumulative power for the test set
  test_targets_cumulative_power = np.cumsum(test_targets_np[:, 0] * test_targets_np[:, 1] * time_diff)
  original_test_rmse = np.sqrt(mean_squared_error(test_targets_cumulative_power, cumulative_power))
- # udtryk for forskellen fra cumulative power på ground truth og cumulative power på vores predictions. Jo tættere på nul, jo strammere hul
+
+ # Udtryk for forskellen fra cumulative power på ground truth og cumulative power på vores predictions.
+ # Jo tættere på nul, jo strammere hul
  print(f"Original Test Root Mean Squared Error (RMSE) for Cumulative Power: {original_test_rmse}")
 
  # Calculate RMSE on the adjusted cumulative power for the test set
  test_rmse = np.sqrt(
  mean_squared_error(test_targets_np[:, 0] * test_targets_np[:, 1], power_consumption_predictions))
- # Udtryk for hvor præcis vores cumulative power på vores predictions er i forhold til sig selv. Store udsving er dårlige.
+ # Udtryk for hvor præcis vores cumulative power på vores predictions er i forhold til sig selv.
+ # Store udsving er dårlige.
  print(f"Adjusted Test Root Mean Squared Error (RMSE) for Cumulative Power: {test_rmse}")
 
  print("Training finished somehow!")
-
- # TODO: Caasper her regnet jeg også bare cumulative power consumption på den simple måde.
- # Her skal den også være integralet i stedet. Du kan bruge dem samme funktion som du laver i trapezoid_integration.
-
-