final commit

2024_10_25/lecture_distances.py

@@ -0,0 +1,65 @@
+import pandas as pd
+import pprint
+import matplotlib.pyplot as plt
+
+# function that check if the difference between two distances is less than 20m
+def check_distance(dist1, dist2):
+    if abs(dist1 - dist2) < 0.05:
+        return True
+    return False
+
+def pt_src(data_df, dist_dict):
+    df = pd.DataFrame(columns=['distance','conductivite','name'])
+    keys = list(dist_dict.keys())
+    for i in range(len(data_df)):
+        for j in range(len(keys)):
+            if check_distance(data_df.iloc[i, 0], keys[j]):
+                new_row = {'distance': keys[j], 'conductivite': data_df.iloc[i, 1], 'name':dist_dict.get(keys[j])}
+                df = df._append(new_row, ignore_index=True)
+    return df
+
+# Function that check if their are double entries based on the name column in the data and only keeps the row with the median distance value
+def remove_double_entries(data_df):
+    data_df = data_df.sort_values(by=['name','distance'])
+    data_df = data_df.drop_duplicates(subset='name', keep='first')
+    return data_df
+
+# Paths to the cleaned data CSV files
+files = [
+    'output/rive_droite_2024.csv',
+    'output/rive_gauche_2024.csv',
+    'output/canoo_2023.csv',
+    'output/canoo_2020.csv'
+]
+
+file_rive_droite = "output\\rive_droite_2024.csv"
+file_rive_gauche = "output\\rive_gauche_2024.csv"
+file_canoo_2023 = "output\canoo_2023.csv"
+file_canoo_2020 = "output\canoo_2020.csv"
+
+file_points_sources_rive_droite = "output\sources\points_sources_rive_droite.csv"
+file_points_sources_rive_gauche = "output\sources\points_sources_rive_gauche.csv"
+file_points_sources_canoo_2023 = "output\sources\points_sources_canoo_2023.csv"
+
+distance_file = "distances.xlsx"
+
+# DataFrames for distances 2023/2024
+df_distances = pd.read_excel(distance_file, skiprows=1)
+distances_2023 = dict(zip(df_distances.iloc[:, 1], df_distances.iloc[:, 0]))
+distances_2024 = dict(zip(df_distances.iloc[:, 2], df_distances.iloc[:, 0]))
+
+# DataFrames for the cleaned data
+df_rive_droite_2024 = pd.read_csv(file_rive_droite)
+df_rive_gauche_2024 = pd.read_csv(file_rive_gauche)
+df_canoo_2023 = pd.read_csv(file_canoo_2023)
+df_canoo_2020 = pd.read_csv(file_canoo_2020)
+
+# DataFrames computation for the sources of the river
+pt_src_rive_droite = remove_double_entries(pt_src(df_rive_droite_2024, distances_2024))
+pt_src_rive_droite.to_csv(file_points_sources_rive_droite, index=False)
+
+pt_src_rive_gauche = remove_double_entries(pt_src(df_rive_gauche_2024, distances_2024))
+pt_src_rive_gauche.to_csv(file_points_sources_rive_gauche, index=False)
+
+pt_src_canoo_2023 = remove_double_entries(pt_src(df_canoo_2023, distances_2023))
+pt_src_canoo_2023.to_csv(file_points_sources_canoo_2023, index=False)

2024_10_25/output/sources/points_sources_canoo_2023.csv

@@ -0,0 +1,14 @@
+distance,conductivite,name
+35.1607891,288.3176,Anglades
+40.48775894,293.005,Anglanat
+18.30798519,227.1419,Ayrissac
+9.453041659,208.1663,Bual
+5.224241888,204.4046,Corn
+13.66500765,214.7027,Cross Renard
+12.16202511,218.6649,Diège
+42.08276949,293.4255,Liauzut
+30.174923070000002,281.1578,Marchepied
+43.47837751,309.5416,Pescalerie
+22.79824485,245.96,Pito
+26.01200193,263.7979,Ressel
+46.31162723,306.0898,Sagne

2024_10_25/output/sources/points_sources_rive_droite.csv

@@ -0,0 +1,13 @@
+distance,conductivite,name
+33.797216829999996,211.924774169921,Anglades
+39.083181992,216.155151367187,Anglanat
+17.5891885989,173.244277954101,Ayrissac
+8.9805148019,164.101013183593,Bual
+4.842451423000001,159.90266418457,Corn
+13.34022860284,168.972229003906,Cross Renard
+11.887356203,166.809005737304,Diège
+29.06627534,204.600280761718,Marchepied
+41.181449136000005,216.37808227539,Pescalerie
+22.042666324000002,176.678253173828,Pito
+25.1455890044,193.875442504882,Ressel
+44.530155019999995,221.792526245117,Sagne

2024_10_25/output/sources/points_sources_rive_gauche.csv

@@ -0,0 +1,14 @@
+distance,conductivite,name
+33.797216829999996,209.5849609375,Anglades
+39.083181992,214.441787719726,Anglanat
+17.5891885989,171.898605346679,Ayrissac
+8.9805148019,162.625411987304,Bual
+4.842451423000001,157.083145141601,Corn
+13.34022860284,167.320678710937,Cross Renard
+11.887356203,165.127410888671,Diège
+40.65562334,215.466522216796,Liauzut
+29.06627534,203.885635375976,Marchepied
+41.181449136000005,215.419143676757,Pescalerie
+22.042666324000002,175.490203857421,Pito
+25.1455890044,192.625335693359,Ressel
+44.530155019999995,220.570251464843,Sagne

2024_10_25/script.py

@@ -0,0 +1,34 @@
+import pandas as pd
+
+# List of file paths
+files = [
+    'rive_droite_2024.xlsx',
+    'rive_gauche_2024.xlsx',
+    'canoo_2023.xlsx',
+    'canoo_2020.xlsx'
+]
+
+# Output paths for cleaned data
+output_paths = [
+    'output/rive_droite_2024.csv',
+    'output/rive_gauche_2024.csv',
+    'output/canoo_2023.csv',
+    'output/canoo_2020.csv'
+]
+
+dfs = []  # List to store cleaned dataframes
+
+for file, output_path in zip(files, output_paths):
+    # Read the Excel file
+    df = pd.read_excel(file)
+
+    # Clean the data
+    df_clean = df.dropna()  # Drop rows with any missing data
+    df_clean = df_clean.apply(pd.to_numeric, errors='coerce')  # Convert all to numeric, coerce errors to NaN
+    df_clean = df_clean.dropna()  # Drop any rows that now have NaNs
+
+    # Save the cleaned dataframe
+    df_clean.to_csv(output_path, index=False)
+
+    # Append the clean dataframe to the list for plotting
+    dfs.append(df_clean)

2024_10_25/script2.py

@@ -0,0 +1,64 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Paths to the cleaned data CSV files
+files = [
+   'output/rive_droite_2024.csv',
+    'output/rive_gauche_2024.csv',
+    'output/canoo_2023.csv',
+    'output/canoo_2020.csv'
+]
+
+sources_files = [
+    'output/sources/points_sources_rive_droite.csv',
+    'output/sources/points_sources_canoo_2023.csv'
+]
+
+colors = ['blue', 'limegreen', 'red', 'purple']  # Colors for each year
+labels = ['2024 Canoe Right Bank', '2024 Canoe Left Bank', '2023 Canoe', '2020 Canoe']  # Labels for each dataset
+
+sources_colors = ['blue', 'red']  # Colors for each year
+
+
+dfs = []  # List to store dataframes
+for file in files:
+    df = pd.read_csv(file)
+    dfs.append(df)
+
+
+sources_dfs = []  # List to store dataframes
+for file in sources_files:
+    df = pd.read_csv(file)
+    sources_dfs.append(df)
+    
+plt.figure(figsize=(12, 8))  # Create a figure with a custom size
+
+for df, color, label in zip(dfs, colors, labels):
+    plt.scatter(df.iloc[:, 0], df.iloc[:, 1], color=color, label=label, alpha=0.8, s=2)  # Plot each year's data
+
+
+for df, color in zip(sources_dfs, sources_colors):
+    bbox_props = dict(boxstyle="round,pad=0.3", fc="white", ec=color, alpha=0.7)
+    for i, row in df.iterrows():
+        plt.scatter(row['distance'], row['conductivite'], color='white', alpha=0.8, s=60, edgecolors='black', linewidth=3)
+        plt.annotate(row['name'], 
+                     (row['distance'], row['conductivite']),
+                     weight='bold' , 
+                     fontsize=11,
+                     xytext=(0, 25),
+                    bbox=bbox_props,
+                    #  arrowprops=dict(facecolor='black', shrink=0.05), 
+                     textcoords='offset points',
+                     ha='center')
+
+
+plt.title('Conductivity by kilometers of river for different year of continuous measurements', y=1 , fontsize = 15, fontweight = 'bold')
+plt.xlabel('Distance (kilometers)')
+plt.ylabel('Conductivity (us/cm)')
+plt.legend(loc='lower right', frameon=True, facecolor='white', edgecolor='black', fancybox=False, framealpha=1)
+plt.grid(True)
+
+# Sauvegarder le graphique
+plt.savefig('output/my_conductivity_plot2.png', format='png', dpi=300, bbox_inches='tight')
+
+plt.show()