pierrelouisbescond

# We extract the list of duplicates files to remove
duplicates = pd.read_excel("./roman-numerals-labeling-plb-20210830.xlsx", sheet_name="duplicates")
duplicates_list = duplicates["file"].tolist()

# as well as the unreadable files 
files_analysis = pd.read_excel("./roman-numerals-labeling-plb-20210830.xlsx", sheet_name="analysis", usecols="B:L")
erroneous_list = files_analysis["file"][files_analysis["to_be_removed"] == 1].tolist()

removal_list = duplicates_list + erroneous_list
print(len(duplicates_list), "duplicates +", len(erroneous_list), "errouneous =", len(removal_list), "pictures to remove.")

pierrelouisbescond

DATA_FOLDER = "./data/"
INITIAL_FOLDERS = ["train", "val", "label_book"]
FOLDERS = ["train", "val"]
LABELS = ["i", "ii", "iii", "iv", "v", "vi", "vii", "viii", "ix", "x"]

initial_folder = FOLDER(DATA_FOLDER, INITIAL_FOLDERS, LABELS)
initial_folder.summary()

pierrelouisbescond

class FOLDER():
    
    def __init__(self, DATA_FOLDER, FOLDERS, LABELS):
        self.DATA_FOLDER = DATA_FOLDER
        self.FOLDERS = FOLDERS
        self.LABELS = LABELS

    def summary(self, display_ratio=4):
        
        for folder in self.FOLDERS:

pierrelouisbescond

pierrelouisbescond

pierrelouisbescond

print("TRAIN PERFORMANCE:\n")
confusion_matrix_train = confusion_matrix(y_train, model.predict(X_train))
confusion_matrix_train = pd.DataFrame(confusion_matrix_train,
                                      index=["Actual_No","Actual_Yes"],
                                      columns=["Predicted_No","Predicted_Yes"])

display(confusion_matrix_train)

recall_resignation_train = confusion_matrix_train.iloc[1,1] / confusion_matrix_train.iloc[1,:].sum()
print("Train Score: {}".format(round(model.score(X_train,y_train),3)))

pierrelouisbescond

pierrelouisbescond

from fdasrsf import fPCA, time_warping, fdawarp, fdahpca

# Functional Alignment
# Align time-series
warp_f = time_warping.fdawarp(f, time)
warp_f.srsf_align()

warp_f.plot()

# Functional Principal Components Analysis

pierrelouisbescond

import pandas as pd
import numpy as np

# Import the CSV file with only useful columns
# source: https://www.data.gouv.fr/fr/datasets/temperature-quotidienne-departementale-depuis-janvier-2018/
df = pd.read_csv("temperature-quotidienne-departementale.csv", sep=";", usecols=[0,1,4])

# Rename columns to simplify syntax
df = df.rename(columns={"Code INSEE département": "Region", "TMax (°C)": "Temp"})

pierrelouisbescond

 # -*- coding: utf-8 -*-

# We start with the import of standard ML librairies
import pandas as pd
import numpy as np
import math

from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor