school = 'Platzi'
print(school) # Incluir la variable declarada anteriormente.
Platzi
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
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=";")
red.head(5)
fixed acidityfloat64
volatile acidityfloat64
0
7.4
0.7
1
7.8
0.88
2
7.8
0.76
3
11.2
0.28
4
7.4
0.7
white.head(5)
fixed acidityfloat64
volatile acidityfloat64
0
7
0.27
1
6.3
0.3
2
8.1
0.28
3
7.2
0.23
4
7.2
0.23
red['category']='red'
white['category']='white'
total_wine = pd.concat([red, white],ignore_index=True )
total_wine
fixed acidityfloat64
3.8 - 15.9
volatile acidityfloat64
0.08 - 1.58
50
8.8
0.66
51
6.6
0.52
52
6.6
0.5
53
8.6
0.38
54
7.6
0.51
55
7.7
0.62
56
10.2
0.42
57
7.5
0.63
58
7.8
0.59
59
7.3
0.39
total_wine.head()
fixed acidityfloat64
volatile acidityfloat64
0
7.4
0.7
1
7.8
0.88
2
7.8
0.76
3
11.2
0.28
4
7.4
0.7
total_wine.shape
total_wine.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6497 entries, 0 to 6496
Data columns (total 13 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 fixed acidity 6497 non-null float64
1 volatile acidity 6497 non-null float64
2 citric acid 6497 non-null float64
3 residual sugar 6497 non-null float64
4 chlorides 6497 non-null float64
5 free sulfur dioxide 6497 non-null float64
6 total sulfur dioxide 6497 non-null float64
7 density 6497 non-null float64
8 pH 6497 non-null float64
9 sulphates 6497 non-null float64
10 alcohol 6497 non-null float64
11 quality 6497 non-null int64
12 category 6497 non-null object
dtypes: float64(11), int64(1), object(1)
memory usage: 660.0+ KB
total_wine.describe()
fixed acidityfloat64
volatile acidityfloat64
count
6497
6497
mean
7.215307065
0.3396659997
std
1.296433758
0.1646364741
min
3.8
0.08
25%
6.4
0.23
50%
7
0.29
75%
7.7
0.4
max
15.9
1.58
quality = total_wine['quality']
quality.describe()
quality.unique()
sns.set_theme(style="darkgrid")
grap_quality = sns.countplot(x="quality", data=total_wine).set(title='Grafica de la calidad para todos los vinos')
total_wine['quality_category'] = total_wine['quality'].apply(lambda x: 'Poor' if x<5 else ('Medium' if x<8 else 'High'))
total_wine.tail()
fixed acidityfloat64
volatile acidityfloat64
6492
6.2
0.21
6493
6.6
0.32
6494
6.5
0.24
6495
5.5
0.29
6496
6
0.21
total_wine.quality_category = total_wine['quality_category'].astype('category')
total_wine.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6497 entries, 0 to 6496
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 fixed acidity 6497 non-null float64
1 volatile acidity 6497 non-null float64
2 citric acid 6497 non-null float64
3 residual sugar 6497 non-null float64
4 chlorides 6497 non-null float64
5 free sulfur dioxide 6497 non-null float64
6 total sulfur dioxide 6497 non-null float64
7 density 6497 non-null float64
8 pH 6497 non-null float64
9 sulphates 6497 non-null float64
10 alcohol 6497 non-null float64
11 quality 6497 non-null int64
12 category 6497 non-null object
13 quality_category 6497 non-null category
dtypes: category(1), float64(11), int64(1), object(1)
memory usage: 666.5+ KB
sns.set_theme(style="darkgrid")
grap_quality = sns.countplot(x="quality_category", data=total_wine).set(title='Grafica de la calidad para todos los vinos por categoria')
0 fixed acidity // acidez fija
fa = total_wine['fixed acidity']
sns.boxplot(x=fa).set_title('Boxplot de la acidez fija');
1 volatile acidity // acidez volátil
va = total_wine['volatile acidity']
sns.boxplot(x=va, color='aqua').set_title('Boxplot de la acidez volátil');
2 citric acid // ácido cítrico
ac = total_wine['citric acid']
sns.boxplot(x=ac, color='lime').set_title('Boxplot del ácido cítrico');
3 residual sugar // azúcar residual
rs = total_wine['residual sugar']
sns.boxplot(x=rs, color='salmon').set_title('Boxplot del azúcar residual ');
4 chlorides // cloruros
cloro = total_wine['chlorides']
sns.boxplot(x=cloro, color='gold').set_title('Boxplot de los cloruros');
5 free sulfur dioxide // dióxido de azufre libre
f_sul_d = total_wine['free sulfur dioxide']
sns.boxplot(x=f_sul_d, color='crimson').set_title('Boxplot del dióxido de azufre libre');
6 total sulfur dioxide // dióxido de azufre total
t_sul_d = total_wine['total sulfur dioxide']
sns.boxplot(x=t_sul_d, color='teal').set_title('Boxplot del dióxido de azufre total');
7 density // densidad
density = total_wine['density']
sns.boxplot(x=density, color='cyan').set_title('Boxplot de la densidad ');
8 pH
ph = total_wine['pH']
sns.boxplot(x=ph, color='r').set_title('Boxplot del pH');
9 sulphates // sulfatos
sul = total_wine['sulphates']
sns.boxplot(x=sul, color='g').set_title('Boxplot de los sulfatos');
10 alcohol
sul = total_wine['sulphates']
sns.boxplot(x=sul, color='g').set_title('Boxplot de los sulfatos');
total_wine.describe()
fixed acidityfloat64
volatile acidityfloat64
count
6497
6497
mean
7.215307065
0.3396659997
std
1.296433758
0.1646364741
min
3.8
0.08
25%
6.4
0.23
50%
7
0.29
75%
7.7
0.4
max
15.9
1.58
#Realizamos una copia del datatframe
total_wine_copy = total_wine.copy()
# Removemos Outliers, creando una función que regresa una lista de index de lso outliers
def outliers(df, col):
"""
Esta función regresa una lista con los indices de los outliers
df: Es el dataframe
columna: Columna donde quieres buscar los outliers
return: Lista con los index de los outliers
"""
Q1 = df[col].quantile(0.25)
Q3 = df[col].quantile(0.75)
IQR = Q3 - Q1
limite_inferior = Q1 - 1.5 * IQR
limite_superior = Q3 + 1.5 * IQR
ls = df.index[(df[col] < limite_inferior) | (df[col] > limite_superior)]
return ls
# Creamos una lista vacia para guardar los indices de las columnas que nos interesa eliminar los outliers
index_list = []
# Creamos un for loop para eliminar los outliers de las columnas
for columna in ['volatile acidity', 'residual sugar', 'chlorides']:
index_list.extend(outliers(total_wine_copy, columna))
print(len(index_list))
print(index_list, '\n')
781
[0, 1, 2, 4, 5, 28, 30, 31, 38, 43, 44, 46, 50, 61, 63, 64, 65, 67, 69, 71, 72, 73, 77, 78, 83, 94, 96, 98, 109, 119, 120, 122, 123, 126, 127, 130, 134, 135, 136, 140, 141, 145, 146, 158, 160, 161, 169, 170, 178, 182, 187, 198, 199, 211, 214, 217, 227, 234, 239, 245, 246, 249, 253, 257, 261, 266, 273, 296, 299, 302, 303, 317, 318, 319, 320, 335, 345, 346, 349, 350, 351, 352, 355, 360, 370, 387, 390, 393, 396, 399, 400, 404, 412, 415, 419, 421, 422, 424, 425, 426, 427, 429, 436, 442, 445, 463, 469, 475, 478, 479, 485, 486, 490, 493, 499, 507, 537, 542, 543, 553, 566, 567, 587, 594, 600, 602, 614, 624, 625, 629, 633, 635, 636, 637, 638, 646, 647, 651, 659, 668, 671, 672, 673, 677, 678, 683, 684, 685, 688, 690, 691, 700, 704, 705, 706, 710, 712, 714, 719, 724, 725, 726, 729, 731, 732, 735, 736, 739, 740, 755, 756, 757, 758, 762, 764, 765, 769, 771, 775, 776, 782, 795, 818, 819, 820, 830, 834, 835, 841, 843, 847, 855, 861, 870, 877, 881, 885, 886, 889, 891, 893, 899, 916, 927, 967, 981, 996, 997, 998, 999, 1012, 1013, 1025, 1027, 1032, 1034, 1037, 1040, 1046, 1064, 1071, 1074, 1094, 1096, 1108, 1115, 1116, 1117, 1119, 1127, 1163, 1164, 1176, 1177, 1178, 1183, 1186, 1189, 1191, 1193, 1194, 1203, 1207, 1231, 1234, 1237, 1238, 1239, 1246, 1252, 1253, 1254, 1261, 1263, 1275, 1277, 1278, 1282, 1290, 1293, 1299, 1301, 1304, 1306, 1307, 1308, 1312, 1316, 1319, 1320, 1321, 1331, 1333, 1334, 1361, 1363, 1366, 1368, 1370, 1372, 1373, 1374, 1376, 1381, 1384, 1385, 1395, 1396, 1399, 1400, 1401, 1410, 1437, 1439, 1441, 1444, 1445, 1447, 1455, 1461, 1467, 1469, 1470, 1471, 1478, 1484, 1486, 1497, 1498, 1499, 1500, 1501, 1505, 1506, 1511, 1512, 1514, 1515, 1519, 1529, 1531, 1542, 1550, 1551, 1552, 1553, 1554, 1556, 1557, 1562, 1563, 1564, 1565, 1567, 1572, 1577, 1578, 1582, 1588, 1589, 1591, 1616, 1619, 1622, 1777, 1820, 1971, 2286, 2547, 2639, 2844, 3000, 3075, 3455, 3531, 3550, 3691, 3753, 3993, 4007, 4016, 4250, 4380, 4621, 4696, 4764, 5127, 5309, 5478, 5638, 6196, 6248, 6249, 6300, 6301, 6391, 6414, 1599, 1606, 1613, 1637, 1638, 1702, 1710, 1773, 1781, 1790, 1824, 1828, 1860, 1864, 1891, 1997, 2002, 2009, 2013, 2043, 2068, 2207, 2229, 2230, 2316, 2361, 2362, 2545, 2642, 2844, 3035, 3053, 3086, 3088, 3123, 3128, 3165, 3207, 3252, 3262, 3279, 3283, 3286, 3321, 3374, 3392, 3447, 3487, 3491, 3492, 3572, 3573, 3650, 3651, 3655, 3763, 3933, 3995, 4010, 4018, 4088, 4091, 4096, 4097, 4099, 4179, 4219, 4380, 4384, 4386, 4608, 4613, 4622, 4730, 4861, 5019, 5037, 5043, 5096, 5144, 5146, 5218, 5222, 5231, 5250, 5252, 5277, 5293, 5300, 5317, 5329, 5479, 5480, 5483, 5487, 5550, 5553, 5613, 5617, 5631, 5633, 5645, 5653, 5706, 5715, 5716, 5880, 5881, 5889, 6054, 6055, 6056, 6079, 6290, 6293, 6347, 6348, 6377, 13, 14, 15, 17, 19, 22, 27, 38, 42, 46, 47, 54, 57, 61, 81, 83, 86, 88, 91, 92, 106, 109, 118, 120, 121, 125, 130, 145, 147, 151, 169, 181, 185, 226, 240, 258, 281, 291, 303, 304, 307, 308, 326, 327, 330, 331, 335, 342, 343, 350, 353, 357, 358, 365, 368, 373, 375, 393, 396, 400, 408, 415, 416, 418, 447, 451, 482, 483, 484, 512, 513, 514, 515, 517, 549, 556, 558, 566, 567, 568, 587, 608, 614, 618, 624, 625, 629, 638, 645, 646, 650, 656, 666, 689, 692, 730, 735, 736, 754, 773, 774, 776, 777, 780, 781, 783, 795, 796, 803, 808, 832, 833, 841, 842, 875, 882, 889, 910, 911, 916, 956, 958, 962, 977, 1008, 1009, 1014, 1020, 1021, 1051, 1094, 1096, 1098, 1109, 1146, 1152, 1155, 1159, 1165, 1166, 1191, 1193, 1194, 1203, 1207, 1220, 1221, 1252, 1258, 1259, 1260, 1277, 1299, 1319, 1331, 1334, 1358, 1360, 1365, 1370, 1371, 1372, 1373, 1374, 1384, 1423, 1434, 1435, 1436, 1474, 1476, 1482, 1504, 1507, 1518, 1519, 1558, 1570, 1578, 1639, 1640, 1653, 1793, 1794, 1795, 1914, 2032, 2083, 2124, 2130, 2199, 2282, 2286, 2328, 2353, 2370, 2371, 2374, 2458, 2476, 2477, 2578, 2579, 2633, 2650, 2757, 2762, 2816, 2853, 2871, 2968, 3150, 3197, 3198, 3237, 3271, 3272, 3313, 3327, 3343, 3434, 3435, 3438, 3464, 3524, 3525, 3623, 3624, 3625, 3785, 3856, 3858, 3878, 3885, 3886, 3948, 3958, 4039, 4075, 4121, 4124, 4178, 4243, 4248, 4303, 4304, 4419, 4448, 4561, 4642, 4648, 4650, 4817, 4882, 4887, 5136, 5226, 5227, 5228, 5334, 5336, 5447, 5501, 5510, 5536, 5571, 5692, 5694, 5772, 5812, 5846, 5898, 5899, 5943, 5945, 5948, 6072, 6079, 6096, 6247, 6297, 6392, 6393, 6412, 6419, 6444]
def remove(df, ls):
ls = sorted(set(ls))
df = df.drop(ls)
return df
total_wine_copy_clean = remove(total_wine_copy, index_list)
total_wine_copy_clean.shape
total_wine_copy_clean.describe()
fixed acidityfloat64
volatile acidityfloat64
count
5772
5772
mean
7.158411296
0.3098016286
std
1.272825161
0.1228351951
min
3.8
0.08
25%
6.4
0.22
50%
6.9
0.28
75%
7.6
0.37
max
15.9
0.655
total_wine_copy_clean
fixed acidityfloat64
3.8 - 15.9
volatile acidityfloat64
0.08 - 0.655
3
11.2
0.28
6
7.9
0.6
7
7.3
0.65
8
7.8
0.58
9
7.5
0.5
10
6.7
0.58
11
7.5
0.5
12
5.6
0.615
16
8.5
0.28
18
7.4
0.59
datos_eliminados = len(total_wine_copy) - len(total_wine_copy_clean)
porcentaje_datos_eliminados = datos_eliminados / len(total_wine_copy) * 100
print(f'Datos del dataframe elimandos: {datos_eliminados}, procentaje de los datos del dataframe elimnados: {porcentaje_datos_eliminados}')
Datos del dataframe elimandos: 725, procentaje de los datos del dataframe elimnados: 11.158996459904571
sns.pairplot(total_wine, corner=True, height=2);
df_for_heatmap = total_wine.iloc[:, :12]
df_for_heatmap
sns.set(rc = {'figure.figsize':(15,8)})
sns.heatmap(df_for_heatmap.corr(), annot=True);
total_wine.corr()[['quality']].sort_values(by='quality', ascending = False)
qualityfloat64
-0.3058579060694202 - 1.0
quality
1
alcohol
0.44431852
citric acid
0.08553171718
free sulfur dioxide
0.05546305862
sulphates
0.03848544588
pH
0.01950570371
residual sugar
-0.03698048459
total sulfur dioxide
-0.04138545386
fixed acidity
-0.07674320791
chlorides
-0.2006655004
sns.jointplot(x = "alcohol", y = "quality", data = total_wine, kind = "scatter");
0 fixed acidity // acidez fija
sns.barplot(x="quality_category", y="fixed acidity", data=total_wine).set_title('Grafíca de barras de la acidez fija');
sns.violinplot(x="quality_category", y="fixed acidity", data=total_wine).set_title('Grafíca de violín de la acidez fija');
1 volatile acidity // acidez volátil
sns.barplot(x="quality_category", y="volatile acidity", data=total_wine).set_title('Grafíca de barras de la acidez volátil');
g1 = sns.violinplot(x="quality_category", y="volatile acidity", data=total_wine)
g1.set_title('Grafíca de violin de la acidez volátil')
g1.set_ylim(0, 1.5);
2 citric acid // ácido cítrico
sns.barplot(x="quality_category", y="citric acid", data=total_wine).set_title('Grafíca de barras del ácido cítrico');
g2 = sns.violinplot(x="quality_category", y="citric acid", data=total_wine)
g2.set_title('Grafíca de violin del ácido cítrico')
g2.set_ylim(-0.25, 1)
3 residual sugar // azúcar residual
sns.barplot(x="quality_category", y="residual sugar", data=total_wine).set_title('Grafíca de barras del azúcar residual');
g3 = sns.violinplot(x="quality_category", y="residual sugar", data=total_wine)
g3.set_ylim(0,25)
g3.set_title('Grafíca de violin del azúcar residual');
4 chlorides // cloruros
sns.barplot(x="quality_category", y="chlorides", data=total_wine).set_title('Grafíca de barras de los cloruros');
g4 = sns.violinplot(x="quality_category", y="chlorides", data=total_wine)
g4.set_ylim(0,.20)
g4.set_title('Grafíca de violin de los cloruros');
5 free sulfur dioxide // dióxido de azufre libre
sns.barplot(x="quality_category", y="free sulfur dioxide", data=total_wine).set_title('Grafíca de barras del dióxido de azufre libre');
g5 = sns.violinplot(x="quality_category", y="free sulfur dioxide", data=total_wine)
g5.set_ylim(0,160)
g5.set_title('Grafíca de violin del dióxido de azufre libre ');
6 total sulfur dioxide // dióxido de azufre total
sns.barplot(x="quality_category", y="total sulfur dioxide", data=total_wine).set_title('Grafíca de barras del dióxido de azufre total');
g6 = sns.violinplot(x="quality_category", y="total sulfur dioxide", data=total_wine)
g6.set_ylim(0,320)
g6.set_title('Grafíca de violin del dióxido de azufre total');
7 density // densidad
sns.barplot(x="quality_category", y="density", data=total_wine).set_title('Grafíca de barras de la densidad ');
g7 = sns.violinplot(x="quality_category", y="density", data=total_wine)
g7.set_ylim(0.985,1.005)
g7.set_title('Grafíca de violin del dióxido de la densidad ');
8 pH
sns.barplot(x="quality_category", y="pH", data=total_wine).set_title('Grafíca de barras del pH ');
g8 = sns.violinplot(x="quality_category", y="pH", data=total_wine)
g8.set_title('Grafíca de violin del dióxido del pH ');
9 sulphates // sulfatos
sns.barplot(x="quality_category", y="sulphates", data=total_wine).set_title('Grafíca de barras de los sulfatos ');
g9 = sns.violinplot(x="quality_category", y="sulphates", data=total_wine)
g9.set_ylim(0, 1.25)
g9.set_title('Grafíca de violin de los sulfatos');
10 alcohol
sns.barplot(x="quality_category", y="alcohol", data=total_wine).set_title('Grafíca de barras del alcohol ');
g10 = sns.violinplot(x="quality_category", y="alcohol", data=total_wine)
g10.set_title('Grafíca de violin del alcohol');