def run(train_csv, train_tensor, test_csv, test_tensor, metric='euclidean'):
print("K means\n")
"""
Construction du dataset train.
"""
df = pd.read_csv(train_csv,
sep=';',
header='infer',
quotechar='"',
low_memory=True)
df = df[['Longitude','Latitude','glc19SpId','scName']]\
.dropna(axis=0, how='all')\
.astype({'glc19SpId': 'int64'})
# target pandas series of the species identifiers (there are 505 labels)
target_df = df['glc19SpId']
# building the environmental data
env_df = build_environmental_data(df[['Latitude', 'Longitude']],
patches_dir=train_tensor)
X_train = env_df.values
y_train = target_df.values
"""
Construction du dataset test.
"""
df = pd.read_csv(test_csv,
sep=';',
header='infer',
quotechar='"',
low_memory=True)
df = df[['Longitude','Latitude','glc19SpId','scName']]\
.dropna(axis=0, how='all')\
.astype({'glc19SpId': 'int64'})
# target pandas series of the species identifiers (there are 505 labels)
target_df = df['glc19SpId']
# building the environmental data
env_df = build_environmental_data(df[['Latitude', 'Longitude']],
patches_dir=test_tensor)
X_test = env_df.values
y_test = target_df.values
"""
Entrainement modèle.
"""
# Standardize the features by removing the mean and scaling to unit variance
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
classifier = VectorModel(metric=metric)
classifier.fit(X_train, y_train)
"""
Évaluation et Calcul de score.
"""
y_predicted = classifier.predict(X_test)
print(f'Top30 score:{classifier.top30_score(y_predicted, y_test)}')
print(f'MRR score:{classifier.mrr_score(y_predicted, y_test)}')
print('Params:', classifier.get_params())
.dropna(axis=0, how='all')\
.astype({'glc19SpId': 'int64'})
# target pandas series of the species identifiers (there are 505 labels)
target_df = df['glc19SpId']
# correspondence table between ids and the species taxonomic names
# (Taxref names with year of discoverie)
taxonomic_names = pd.read_csv('../data/occurrences/taxaName_glc19SpId.csv',
sep=';',
header='infer',
quotechar='"',
low_memory=True)
# building the environmental data
env_df = build_environmental_data(df[['Latitude', 'Longitude']],
patches_dir='example_envtensors')
X = env_df.values
y = target_df.values
# Standardize the features by removing the mean and scaling to unit variance
scaler = StandardScaler()
X = scaler.fit_transform(X)
# Evaluate as the average accuracy on one train/split random sample:
print("Test nearest centroid model")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
classifier = NearestCentroidModel(metric='euclidean')
classifier.fit(X_train, y_train)
y_predicted = classifier.predict(X_test)
print(f'Top30 score:{classifier.top30_score(y_predicted, y_test)}')
print(f'MRR score:{classifier.mrr_score(y_predicted, y_test)}')
print('Params:', classifier.get_params())