import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns # agrega librerías que necesites

url_wine_red = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv' url_wine_white = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv'

red = pd.read_csv(url_wine_red, delimiter=";") white = pd.read_csv(url_wine_white, delimiter=";") wine_red = pd.DataFrame(red) wine_white = pd.DataFrame(white)

wine_red.head(5)

wine_white.head(5)

red['category']='wine_red' white['category']='wine_white'

total_wine = pd.concat([wine_white, wine_red], ignore_index=True) total_wines = pd.DataFrame(total_wine)

total_wine

rows_wine_red = len(wine_red.axes[0]) columns_wine_red = len(wine_red.axes[1]) rows_wine_white = len(wine_white.axes[0]) columns_wine_white = len(wine_white.axes[1])

print(rows_wine_red) print(columns_wine_red)

print(rows_wine_white) print(columns_wine_white)

total_wines.info()

total_wines.describe()

quality_wine = total_wines['quality'] quality_wine

quality_wine.unique()

count_points = quality_wine.value_counts() print(count_points)

sns.set_theme(style="whitegrid") sns.countplot(quality_wine).set(title='Calidad en Vinos')

total_wines['quality_category'] = total_wines['quality'].apply(lambda x : 'Poor' if x<5 else ('Medium' if x<8 else 'High')) total_wines.tail()

total_wines.quality_category = total_wines['quality_category'].astype('category') total_wines.info()

sns.set_theme(style="whitegrid") graph_quality = sns.countplot(x="quality_category", data=total_wine).set(title='Categorías de calidad en los Vinos')

ph = total_wines['pH'] sns.boxplot(x=ph, color='yellow').set_title('Distribución del pH')

density = total_wines['density'] sns.boxplot(x=density, color='red').set_title('Distribución de la Densidad')

alcohol = total_wines['alcohol'] sns.boxplot(x=alcohol, color='cyan').set_title('Distribución del Alcohol')

residual_sugar = total_wines['residual sugar'] sns.boxplot(x=residual_sugar, color='brown').set_title('Distribución del Azúcar')

citric_acid = total_wines['citric acid'] sns.boxplot(x=citric_acid, color='yellow').set_title('Distribución del Ácido Cítrico')

volatile_acidity = total_wines['volatile acidity'] sns.boxplot(x=volatile_acidity, color='red').set_title('Distribución de la Acidez Volátil')

fixed_acidity = total_wines['fixed acidity'] sns.boxplot(x=fixed_acidity, color='grey').set_title('Distribución del Ácido Fijo')

chlorides = total_wines['chlorides'] sns.boxplot(x=chlorides, color='red').set_title('Distribución de los Cloruros')

free_sulfur_dioxide = total_wines['free sulfur dioxide'] sns.boxplot(x=free_sulfur_dioxide, color='blue').set_title('Distribución del Dióxido de Azufre Libre')

total_sulfure_dioxide = total_wines['total sulfur dioxide'] sns.boxplot(x=total_sulfure_dioxide, color='cyan').set_title('Ditribución de Azufre Total')

sulphates = total_wines['sulphates'] sns.boxplot(x=sulphates, color='green').set_title('Distribución de Sulfatos')

total_wines_copy = total_wines.copy()

def outliers(df, columna): Q1 = df[columna].quantile(0.25) Q3 = df[columna].quantile(0.75) IQR = Q3 - Q1 limite_inferior = Q1 - 1.5*IQR limite_superior = Q3 + 1.5*IQR ls = df.index[(df[columna] < limite_inferior) | (df[columna] > limite_superior)] return ls

indices_list = [] for columna in ['volatile acidity', 'residual sugar', 'chlorides']: indices_list.extend(outliers(total_wines_copy, columna)) print(len(indices_list)) print(indices_list, '\n')

def remove(df, ls): ls = sorted(set(ls)) df = df.drop(ls) return df total_wines_copy_clean = remove(total_wines_copy, indices_list) total_wines_copy_clean.shape

total_wines_copy_clean

total_wines_copy_clean.describe()

total_deleted_data = len(total_wines_copy) - len(total_wines_copy_clean) print(total_deleted_data)

porc_deleted_data = total_deleted_data / len(total_wines_copy) * 100 print(porc_deleted_data)

sns.pairplot(total_wines, corner=True, height=2)

df_heatmap = total_wine.iloc[:, :12] df_heatmap sns.set(rc = {'figure.figsize':(10,8)}) sns.heatmap(df_heatmap.corr(), annot=True)

total_wines.corr()[['quality']].sort_values(by='quality', ascending = False)

sns.jointplot(x = "alcohol", y = "quality", data = total_wines, kind = "scatter")

sns.barplot(x="quality_category", y="alcohol", data=total_wines).set_title('Grafíca de barras del Alcohol')

sns.violinplot(x="quality_category", y="alcohol", data=total_wine).set_title('Grafíca de barras del Alcohol')

sns.barplot(x="quality_category", y="citric acid", data=total_wines).set_title('Grafíca de barras del Ácido Cítrico')

sns.violinplot(x="quality_category", y="citric acid", data=total_wines).set_title('Grafíca de barras del Ácido Cítrico')

sns.barplot(x="quality_category", y="free sulfur dioxide", data=total_wines).set_title('Grafíca de barras del Dióxido de Azufre Libre')

sns.violinplot(x="quality_category", y="free sulfur dioxide", data=total_wines).set_title('Grafíca de barras del Dióxido de Azufre Libre')