Merge pull request #27 from denBruneBarone/heatmap

Heatmap

data_processing/energy_consumption/datapoints_summation.py

@@ -1,22 +1,12 @@
-def calculate_energy_by_summing(data):
-
- # Calculate power consumption for each row
- data['power'] = data['battery_voltage'] * data['battery_current']
-
- # Group data by flight and sum power consumption for each flight
- flight_groups = data.groupby('flight')
- flight_energy = {}
- for flight, flight_data in flight_groups:
- total_energy = 0
- total_energy_wh = 0
- prev_time = flight_data['time'].iloc[0]
- for index, row in flight_data.iterrows():
- time_interval = row['time'] - prev_time
- total_energy += row['power'] * time_interval
- prev_time = row['time']
- total_energy_wh = total_energy / 3600
- flight_energy[flight] = total_energy_wh
- return flight_energy
-
-
-
+import numpy as np
+
+
+def add_power_to_df(df):
+ df['time_interval'] = df['time'].diff().fillna(0)
+ # Unit of power
+ df['power_w'] = df['battery_voltage'] * df['battery_current']
+ # Unit of energy
+ df['energy_j'] = df['battery_voltage'] * df['battery_current'] * df['time_interval']
+ df['cumulative_power'] = np.cumsum(df['energy_j'])
+ df.drop(columns=['time_interval'], inplace=True)
+ return df

data_processing/energy_consumption/trapeziod_integration.py

@@ -38,15 +38,6 @@ def integrate_flight_data(df):
  return flight_energy
 
 
-def add_power_to_df(df):
- df['power_consumption'] = df['battery_voltage'] * df['battery_current']
- df = df.sort_values(by='time')
- df['time_difference'] = df['time'].diff().fillna(0)
- df['power_in_row'] = df['power_consumption'] * df['time_difference']
- df['cumulative_power'] = np.cumsum(df['power_in_row'])
- return df
-
-
 def integrate_specific_flight_data(data):
  """Integrate power consumption for flight 1 and convert to watt-hours."""
  flight_energy = {}

data_processing/heatmap.py

@@ -0,0 +1,46 @@
+import seaborn as sns
+import matplotlib.pyplot as plt
+import pandas as pd
+import os
+from machine_learning.prepare_for_training import format_data
+from machine_learning.pre_processing import *
+
+PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "../"))
+file_path = os.path.join(PROJECT_ROOT, "data/datasets/rodrigues/flights_processed.csv")
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+import pandas as pd
+import os
+from machine_learning.prepare_for_training import format_data
+from machine_learning.pre_processing import *
+
+
+def generate_correlation_heatmaps(file_path, cutoff=0.09):
+ # Extract csv data
+ df = load_data(file_path)
+
+ # Remove unwanted columns
+ list_df = format_data(df)
+
+ # Compute the correlation matrix
+ corr_matrix = list_df.corr()
+
+ # Generate the full heatmap
+ plt.figure(figsize=(20, 16))
+ sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt=".2f")
+ plt.title('Full Correlation Heatmap')
+ plt.show()
+
+ # Generate the heatmap for strong relationships
+ plt.figure(figsize=(20, 16))
+ strong_corr_matrix = corr_matrix.copy()
+ strong_corr_matrix[abs(corr_matrix) <= cutoff] = None
+ sns.heatmap(strong_corr_matrix, annot=True, cmap='coolwarm', fmt=".2f")
+ plt.title('Correlation Heatmap for Strong Relationships (cutoff={})'.format(cutoff))
+ plt.show()
+
+
+generate_correlation_heatmaps(file_path)
+
+

machine_learning/prepare_for_training.py

@@ -1,4 +1,4 @@
-from data_processing.energy_consumption.trapeziod_integration import add_power_to_df
+from data_processing.energy_consumption.datapoints_summation import add_power_to_df
 from sklearn.preprocessing import StandardScaler
 import pandas as pd
 
@@ -7,7 +7,7 @@ class TrainingDataset:
  def __init__(self, data):
  self.data = data
  self.scaler = StandardScaler()
- self.fit_scaler()  # Laver og fitter en scaler ved initialisation.
+ self.fit_scaler() # Laver og fitter en scaler ved initialisation.
 
  # Kigger på alt given data, ikke bare en enkelt dataframe. Konstruerer en passende scaler.
  def fit_scaler(self):
@@ -54,14 +54,24 @@ def __getitem__(self, index):
  return normalized_input, target_array
 
 
-def format_data(array_of_df):
- formatted_array = []
- for df in array_of_df:
+def format_data(input_data):
+ if isinstance(input_data, list):
+ formatted_array = []
+ for df in input:
+ df['position_x'] = df['position_x'] - df['position_x'].iloc[0]
+ df['position_y'] = df['position_y'] - df['position_y'].iloc[0]
+ df['position_z'] = df['position_z'] - df['position_z'].iloc[0]
+
+ df = df.drop(columns=['flight', 'speed', 'altitude', 'date', 'time_day', 'route'])
+ df = add_power_to_df(df)
+ formatted_array.append(df)
+ return formatted_array
+ elif isinstance(input_data, pd.DataFrame):
+ df = input_data
  df['position_x'] = df['position_x'] - df['position_x'].iloc[0]
  df['position_y'] = df['position_y'] - df['position_y'].iloc[0]
  df['position_z'] = df['position_z'] - df['position_z'].iloc[0]
 
  df = df.drop(columns=['flight', 'speed', 'altitude', 'date', 'time_day', 'route'])
  df = add_power_to_df(df)
- formatted_array.append(df)
- return formatted_array
+ return df