tests celia

Author: celiacnavarro

test/img/0/python.png

@@ -0,0 +1,43 @@
+
+import pandas as pd
+import pytest
+
+from toolkit.data_processing import buffdescribe
+from toolkit.data_analysis import *
+from toolkit.machine_learning import *
+from toolkit.plot import *
+
+@pytest.fixture
+
+def test_df():
+    return pd.DataFrame({'a': [1, 2, 3], 'b': ['x', 'y', 'z'], 'c': [4.5, 6.7, 8.9]})
+
+def test_buffdescribe_columns(test_df):
+    result = buffdescribe(test_df)
+    assert result.index.tolist() == ['a', 'b', 'c']
+
+def test_buffdescribe_data_type(test_df):
+    result = buffdescribe(test_df)
+    assert result['DATA_TYPE'].tolist() == ['int64', 'object', 'float64']
+
+def test_buffdescribe_null_values(test_df):
+    result = buffdescribe(test_df)
+    assert result['MISSINGS (%)'].tolist() == [0.0, 0.0, 0.0]
+
+def test_buffdescribe_non_null_values(test_df):
+    result = buffdescribe(test_df)
+    assert result['NOT_NULL'].tolist() == [3, 3, 3]
+
+def test_buffdescribe_unique_values(test_df):
+    result = buffdescribe(test_df)
+    assert result['UNIQUE_VALUES'].tolist() == [3, 3, 3]
+
+def test_buffdescribe_cardinality(test_df):
+    result = buffdescribe(test_df)
+    assert result['CARDIN (%)'].tolist() == [100.0, 100.0, 100.0]
+
+def test_buffdescribe_descriptive_statistics(test_df):
+    result = buffdescribe(test_df)
+    assert result.columns.tolist() == ['DATA_TYPE', 'MISSINGS (%)', 'NOT_NULL', 'UNIQUE_VALUES', 'CARDIN (%)',
+                                       'mean', 'median', 'std']
+

test/img/1/ejercicios.png

@@ -0,0 +1,26 @@
+import pytest
+import pandas as pd
+
+from toolkit.data_processing import clean_text
+from toolkit.data_analysis import *
+from toolkit.machine_learning import *
+from toolkit.plot import *
+
+@pytest.fixture
+
+def test_data():
+    # Crea un conjunto de datos de prueba para la función clean_text
+    data = {'text': ['Este es un texto de prueba', 'Otro texto de prueba'],
+            'target': [0, 1]}
+    df = pd.DataFrame(data)
+    return df
+
+def test_clean_text(test_data):
+    # Ejecuta la función clean_text con el conjunto de datos de prueba
+    result = clean_text(test_data, 'text', 'spanish', 'target', 'test.csv')
+    expected_columns = ['text', 'target']
+    expected_result = pd.DataFrame({'text': ['text prueb', 'text prueb'], 'target': [0, 1]})
+    
+    # Verifica que el resultado es igual al esperado
+    assert result.columns.tolist() == expected_columns
+    assert result.equals(expected_result)

test/test_buffdescribe.py

@@ -0,0 +1,28 @@
+# Importa la función a testear
+from toolkit.data_processing import load_imgs
+from toolkit.data_analysis import *
+from toolkit.machine_learning import *
+from toolkit.plot import *
+
+import pandas as pd
+import numpy as np
+import os
+import pytest
+
+
+def test_load_imgs():
+    # Define algunos parámetros de prueba
+    path = os.getcwd() + '\\img'
+    im_size = 64
+    
+    # Llama a la función de prueba y obtiene los resultados
+    df, X_train, y_train = load_imgs(path, im_size)
+    
+    # Comprueba si los resultados devueltos son los esperados
+    assert isinstance(df, pd.DataFrame)
+    assert isinstance(X_train, np.ndarray)
+    assert isinstance(y_train, np.ndarray)
+    assert df.shape[0] == len(X_train) == len(y_train)
+    assert set(df.columns) == set(['filename', 'category'])
+    assert set(df['category'].unique()) == set(range(len(os.listdir(path))))
+

test/test_clean_text.py

@@ -0,0 +1,18 @@
+from toolkit.data_processing import *
+from toolkit.data_analysis import *
+from toolkit.machine_learning import *
+from toolkit.plot import plot_ngrams
+
+import pandas as pd
+import numpy as np
+import plotly.graph_objs as go
+import pytest
+
+
+def test_plot_ngrams():
+    df = pd.DataFrame({'target': [1, 0, 1], 'text': ['foo bar foo', 'baz qux', 'foo bar baz']})
+    n_gram = 2
+    fig = plot_ngrams(df, 'target', 'text', n_gram)
+    assert isinstance(fig, go.Figure)
+    assert len(fig['data']) == 2
+