大作业
- 导入鸢尾花数据
import numpy as np
import pandas as pd
from pandas import plotting
import matplotlib.pyplot as plt
plt.style.use('seaborn')
import seaborn as sns
sns.set_style("whitegrid")
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.neighbors import KNeighborsClassifier
from sklearn import svm
from sklearn import metrics
from sklearn.tree import DecisionTreeClassifier
iris = r'D:\iris.csv'
#或iris = pd.read_csv('F:\pydata\dataset\kaggle\iris.csv', usecols=[1, 2, 3, 4, 5])
iris_data = np.loadtxt(iris, dtype=object, delimiter=',', skiprows=1)
print(iris_data[0:10])
#
[['5.1' '3.5' '1.4' '0.2' 'setosa']
['4.9' '3.0' '1.4' '0.2' 'setosa']
['4.7' '3.2' '1.3' '0.2' 'setosa']
['4.6' '3.1' '1.5' '0.2' 'setosa']
['5.0' '3.6' '1.4' '0.2' 'setosa']
['5.4' '3.9' '1.7' '0.4' 'setosa']
['4.6' '3.4' '1.4' '0.3' 'setosa']
['5.0' '3.4' '1.5' '0.2' 'setosa']
['4.4' '2.9' '1.4' '0.2' 'setosa']
['4.9' '3.1' '1.5' '0.1' 'setosa']]
- 求鸢尾属植物萼片长度的平均值,中位数,标准差
sepalLength = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0])
print(sepalLength[0:10])
#[5.1 4.9 4.7 4.6 5. 5.4 4.6 5. 4.4 4.9]
print(np.mean(sepalLength))
#5.843333333333334
print(np.median(sepalLength))
#5.8
print(np.std(sepalLength))
#0.8253012917851409
- 创建一种标准化形式的鸢尾属植物萼片的长度,起值正好介于0和1之间,这样最小值为0,最大值为1(第1列,sepallength)
sepalLength = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1,usecols=[0])
aMin = np.amin(sepalLength)
aMax = np.amax(sepalLength)
x = (sepalLength - aMin) / np.ptp(sepalLength)
print(x[0:10])
#[0.22222222 0.16666667 0.11111111 0.08333333 0.19444444 0.30555556
0.08333333 0.19444444 0.02777778 0.16666667]
- 找到鸢尾属植物萼片长度的第5和第95百分位数
sepalLength = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1,usecols=[0])
x = np.percentile(sepalLength,[5, 95])
print(x)
#[4.6 7.255]
- 把iris_data数据集中的20个随机位置改为np.nan值
iris_data = np.loadtxt(iris, dtype=object, delimiter=',', skiprows=1)
i, j = iris_data.shape
np.random.seed(20200621)
iris_data[np.random.randint(i, size=20), np.random.randint(j, size=20)] = np.nan #或用np.random.choice函数
print(iris_data[0:10])
#[['5.1' '3.5' '1.4' '0.2' 'setosa']
['4.9' '3.0' '1.4' '0.2' 'setosa']
['4.7' '3.2' '1.3' '0.2' 'setosa']
['4.6' '3.1' '1.5' '0.2' 'setosa']
['5.0' '3.6' '1.4' '0.2' 'setosa']
['5.4' nan '1.7' '0.4' 'setosa']
['4.6' '3.4' '1.4' '0.3' 'setosa']
['5.0' '3.4' '1.5' '0.2' 'setosa']
['4.4' '2.9' '1.4' '0.2' nan]
['4.9' '3.1' '1.5' '0.1' 'setosa']]
- 在iris_data的sepallength中查找缺失值的个数和位置(第1列)
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1,usecols=[0, 1, 2, 3])
i, j = iris_data.shape
np.random.seed(20200621)
iris_data[np.random.randint(i, size=20), np.random.randint(j, size=20)] = np.nan
sepallength = iris_data[:, 0]
x = np.isnan(sepallength)
print(x)
print(np.where(x))
#[False False False False False False False False False False False False
False False False False False False False False False False False False
False False True False False False False False False False False False
False False False False False False False False True False False False
False False False False False False False True False False False False
False False False True False False False False False False False False
False False False False False False False False False False False False
False False False False False False True False False False False False
False False False False False False False False False False False False
False False False False False False False True False False False False
False False False False False False False False False False False False
False False False False False False False False False False False False
False False False False False False]
(array([ 26, 44, 55, 63, 90, 115], dtype=int32),)
- 筛选具有 sepallength(第1列)< 5.0 并且 petallength(第3列)> 1.5 的 iris_data行
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
sepallength = iris_data[:, 0]
petallength = iris_data[:, 2]
index = np.where(np.logical_and(petallength > 1.5, sepallength < 5))
print(iris_data[index])
#[[4.8 3.4 1.6 0.2]
[4.8 3.4 1.9 0.2]
[4.7 3.2 1.6 0.2]
[4.8 3.1 1.6 0.2]
[4.9 2.4 3.3 1. ]
[4.9 2.5 4.5 1.7]]
- 选择没有任何 nan 值的 iris_data行
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
i, j = iris_data.shape
np.random.seed(20200621)
iris_data[np.random.randint(i, size=20), np.random.randint(j, size=20)] = np.nan
x = iris_data[np.sum(np.isnan(iris_data), axis=1) == 0]
print(x[0:10])
#[[5.1 3.5 1.4 0.2]
[4.9 3. 1.4 0.2]
[4.7 3.2 1.3 0.2]
[4.6 3.1 1.5 0.2]
[5. 3.6 1.4 0.2]
[4.6 3.4 1.4 0.3]
[5. 3.4 1.5 0.2]
[4.9 3.1 1.5 0.1]
[5.4 3.7 1.5 0.2]
[4.8 3.4 1.6 0.2]]
- 计算 iris_data 中sepalLength(第1列)和petalLength(第3列)之间的相关系数
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
sepallength = iris_data[:, 0]
petallength = iris_data[:, 2]
x = np.corrcoef(sepallength, petallength)
print(x)
#[[1. 0.87175378]
[0.87175378 1. ]]
- 找出iris_data是否有任何缺失值
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
x = np.isnan(iris_data)
print(np.any(x))
#False
- 在numpy数组中将所有出现的nan替换为0
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
i, j = iris_data.shape
np.random.seed(20200621)
iris_data[np.random.choice(i, size=20), np.random.choice(j, size=20)] = np.nan
iris_data[np.isnan(iris_data)] = 0
print(iris_data[0:10])
#[[5.1 3.5 1.4 0.2]
[4.9 3. 1.4 0.2]
[4.7 3.2 1.3 0.2]
[4.6 3.1 1.5 0.2]
[5. 3.6 1.4 0.2]
[5.4 0. 1.7 0.4]
[4.6 3.4 1.4 0.3]
[5. 3.4 1.5 0.2]
[4.4 2.9 0. 0.2]
[4.9 3.1 1.5 0.1]]
- 找出鸢尾属植物物种中的唯一值和唯一值出现的数量
iris_data = np.loadtxt(iris, dtype=object, delimiter=',', skiprows=1, usecols=[4])
x = np.unique(iris_data, return_counts=True)
print(x)
(array(['setosa', 'versicolor', 'virginica'], dtype=object), array([50, 50, 50]))
- 将 iris_data 的花瓣长度(第3列)以形成分类变量的形式显示。定义:Less than 3 -->‘small’;3-5 --> ‘medium’;’>=5 --> ‘large’
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
petal_length_bin = np.digitize(iris_data[:, 2], [0, 3, 5, 10])
label_map = {1: 'small', 2: 'medium', 3: 'large', 4: np.nan}
petal_length_cat = [label_map[x] for x in petal_length_bin]
print(petal_length_cat[0:10])
#['small', 'small', 'small', 'small', 'small', 'small', 'small', 'small', 'small', 'small']
- 在 iris_data 中创建一个新列,其中 volume 是 (pi x petallength x sepallength ^ 2)/ 3
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
sepallength = iris_data[:, 0]
petallength = iris_data[:, 2]
volume = (np.pi * petallength * sepallength ** 2) / 3
volume = volume[:, np.newaxis]
iris_data = np.concatenate([iris_data, volume], axis=1)
print(iris_data[0:10])
#[[ 5.1 3.5 1.4 0.2 38.13265163]
[ 4.9 3. 1.4 0.2 35.20049849]
[ 4.7 3.2 1.3 0.2 30.07237208]
[ 4.6 3.1 1.5 0.2 33.23805027]
[ 5. 3.6 1.4 0.2 36.65191429]
[ 5.4 3.9 1.7 0.4 51.91167701]
[ 4.6 3.4 1.4 0.3 31.02218026]
[ 5. 3.4 1.5 0.2 39.26990817]
[ 4.4 2.9 1.4 0.2 28.38324243]
[ 4.9 3.1 1.5 0.1 37.71481981]]
- 随机抽鸢尾属植物的种类,使得Iris-setosa的数量是Iris-versicolor和Iris-virginica数量的两倍
species = np.array(['Iris‐setosa', 'Iris‐versicolor', 'Iris‐virginica'])
species_out = np.random.choice(species, 10000, p=[0.5, 0.25, 0.25])
print(np.unique(species_out, return_counts=True))
#(array(['Iris‐setosa', 'Iris‐versicolor', 'Iris‐virginica'], dtype='<U15'), array([5042, 2534, 2424]))
- 根据 sepallength 列对数据集进行排序
iris_data = np.loadtxt(iris, dtype=object, delimiter=',', skiprows=1)
sepallength = iris_data[:, 0]
index = np.argsort(sepallength)
print(iris_data[index][0:10])
#[['4.3' '3.0' '1.1' '0.1' 'setosa']
['4.4' '3.2' '1.3' '0.2' 'setosa']
['4.4' '3.0' '1.3' '0.2' 'setosa']
['4.4' '2.9' '1.4' '0.2' 'setosa']
['4.5' '2.3' '1.3' '0.3' 'setosa']
['4.6' '3.6' '1.0' '0.2' 'setosa']
['4.6' '3.1' '1.5' '0.2' 'setosa']
['4.6' '3.4' '1.4' '0.3' 'setosa']
['4.6' '3.2' '1.4' '0.2' 'setosa']
['4.7' '3.2' '1.3' '0.2' 'setosa']]
- 在鸢尾属植物数据集中找到最常见的花瓣长度值(第3列)
iris_data = np.loadtxt(iris, dtype=object, delimiter=',', skiprows=1)
petallength = iris_data[:, 2]
vals, counts = np.unique(petallength, return_counts=True)
print(vals[np.argmax(counts)])
print(np.amax(counts))
#1.4
13
- 在鸢尾花数据集的 petalwidth(第4列)中查找第一次出现的值大于1.0的位置
iris_data = np.loadtxt(iris, dtype=float, delimiter=',', skiprows=1, usecols=[0, 1, 2, 3])
petalWidth = iris_data[:, 3]
index = np.where(petalWidth > 1.0)
print(index)
print(index[0][0])
#(array([ 50, 51, 52, 53, 54, 55, 56, 58, 59, 61, 63, 64, 65,
66, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 80,
82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 94, 95,
96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108,
109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121,
122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134,
135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147,
148, 149], dtype=int32),)
50