import pandas as pd
df=pd.read_csv('',sep=';')
这是如果出现; 说明是用;做分隔符，而不是默认的,
import pandas as pd
red_df = pd.read_csv('winequality-red.csv', sep=';')
white_df = pd.read_csv('winequality-white.csv', sep=';')
red_df.head()
white_df.head()
| fixed_acidity | volatile_acidity | citric_acid | residual_sugar | chlorides | free_sulfur_dioxide | total_sulfur_dioxide | density | pH | sulphates | alcohol | quality | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 7.0 | 0.27 | 0.36 | 20.7 | 0.045 | 45.0 | 170.0 | 1.0010 | 3.00 | 0.45 | 8.8 | 6 |
| 1 | 6.3 | 0.30 | 0.34 | 1.6 | 0.049 | 14.0 | 132.0 | 0.9940 | 3.30 | 0.49 | 9.5 | 6 |
| 2 | 8.1 | 0.28 | 0.40 | 6.9 | 0.050 | 30.0 | 97.0 | 0.9951 | 3.26 | 0.44 | 10.1 | 6 |
| 3 | 7.2 | 0.23 | 0.32 | 8.5 | 0.058 | 47.0 | 186.0 | 0.9956 | 3.19 | 0.40 | 9.9 | 6 |
| 4 | 7.2 | 0.23 | 0.32 | 8.5 | 0.058 | 47.0 | 186.0 | 0.9956 | 3.19 | 0.40 | 9.9 | 6 |
print(red_df.shape)
(1599, 12)
print(white_df.shape)
(4898, 12)
red_df.isnull().sum()
fixed_acidity 0 volatile_acidity 0 citric_acid 0 residual_sugar 0 chlorides 0 free_sulfur_dioxide 0 total_sulfur-dioxide 0 density 0 pH 0 sulphates 0 alcohol 0 quality 0 dtype: int64
white_df.isnull().sum()
fixed_acidity 0 volatile_acidity 0 citric_acid 0 residual_sugar 0 chlorides 0 free_sulfur_dioxide 0 total_sulfur_dioxide 0 density 0 pH 0 sulphates 0 alcohol 0 quality 0 dtype: int64
white_df.duplicated().sum() 重复值统计
937 但是重复行是不可以删除的
红葡萄酒数据集中有多少唯一的质量值？
red_df.quality.nunique()
6
红葡萄酒数据集中的平均密度是多少？
red_df.density.mean()
0.996746679174484
import numpy as np
a=np.random.random(1000)
生成1000个随机数的矩阵
np.mean(a)
求a得平均值
# 导入 numpy 和 pandas
import numpy as np
import pandas as pd
# 加载红葡萄酒和白葡萄酒数据集
red_df = pd.read_csv('winequality-red.csv', sep=';')
white_df = pd.read_csv('winequality-white.csv', sep=';')
# 为红葡萄酒数据框创建颜色数组
color_red = np.repeat('red', red_df.shape[0])
# 为白葡萄酒数据框创建颜色数组
color_white = np.repeat('white', white_df.shape[0])
red_df['color'] = color_red
red_df.head()
| fixed_acidity | volatile_acidity | citric_acid | residual_sugar | chlorides | free_sulfur_dioxide | total_sulfur-dioxide | density | pH | sulphates | alcohol | quality | color | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 7.4 | 0.70 | 0.00 | 1.9 | 0.076 | 11.0 | 34.0 | 0.9978 | 3.51 | 0.56 | 9.4 | 5 | red |
| 1 | 7.8 | 0.88 | 0.00 | 2.6 | 0.098 | 25.0 | 67.0 | 0.9968 | 3.20 | 0.68 | 9.8 | 5 | red |
| 2 | 7.8 | 0.76 | 0.04 | 2.3 | 0.092 | 15.0 | 54.0 | 0.9970 | 3.26 | 0.65 | 9.8 | 5 | red |
| 3 | 11.2 | 0.28 | 0.56 | 1.9 | 0.075 | 17.0 | 60.0 | 0.9980 | 3.16 | 0.58 | 9.8 | 6 | red |
| 4 | 7.4 | 0.70 | 0.00 | 1.9 | 0.076 | 11.0 | 34.0 | 0.9978 | 3.51 | 0.56 | 9.4 | 5 | red |
# 附加数据框
wine_df = red_df.append(white_df)
# 查看数据框，检查是否成功
wine_df.head()
| alcohol | chlorides | citric_acid | color | density | fixed_acidity | free_sulfur_dioxide | pH | quality | residual_sugar | sulphates | total_sulfur-dioxide | total_sulfur_dioxide | volatile_acidity | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 9.4 | 0.076 | 0.00 | red | 0.9978 | 7.4 | 11.0 | 3.51 | 5 | 1.9 | 0.56 | 34.0 | NaN | 0.70 |
| 1 | 9.8 | 0.098 | 0.00 | red | 0.9968 | 7.8 | 25.0 | 3.20 | 5 | 2.6 | 0.68 | 67.0 | NaN | 0.88 |
| 2 | 9.8 | 0.092 | 0.04 | red | 0.9970 | 7.8 | 15.0 | 3.26 | 5 | 2.3 | 0.65 | 54.0 | NaN | 0.76 |
| 3 | 9.8 | 0.075 | 0.56 | red | 0.9980 | 11.2 | 17.0 | 3.16 | 6 | 1.9 | 0.58 | 60.0 | NaN | 0.28 |
| 4 | 9.4 | 0.076 | 0.00 | red | 0.9978 | 7.4 | 11.0 | 3.51 | 5 | 1.9 | 0.56 | 34.0 | NaN | 0.70 |
将新组合的数据框保存为 winequality_edited.csv。务必设置 index=False，以避免保存未命名列！
wine_df.to_csv('winequality_edited.csv', index=False)
new_labels=list(red_df.columns)
new_labels[6]='total_sulfur_dioxide'
red_df.columns=new_labels
groupby函数
red_df.groupby('quality').mean()
求出平均值
red_df.groupby(['quality','color']).mean()
red_df.groupby(['quality','color'],as_index=False).mean()
不用颜色和质量做索引as_index=False
只对某一列做平均值
red_df.groupby(['quality','color'],as_index=False)['ph'].mean()
df.groupby('color').mean().quality
df.describe().pH
bin_edges = [2.72, 3.11, 3.21, 3.32, 4.01]
bin_names = ['high', 'mod_high', 'medium', 'low']
df['acidity_levels'] = pd.cut(df['pH'], bin_edges, labels=bin_names)
df.head()
df.groupby('acidity_levels').mean().quality
df.to_csv('winequality_edited.csv', index=False)
等效语句
# selecting malignant records in cancer data
df_m = df[df['diagnosis'] == 'M']
df_m = df.query('diagnosis == "M"')
# selecting records of people making over $50K
df_a = df[df['income'] == ' >50K']
df_a = df.query('income == " >50K"')# get the median amount of alcohol content
# 获取酒精含量的中位数 df.alcohol.median()
# 选择酒精含量小于中位数的样本
low_alcohol =df[df.alcohol < 10.3]
# 选择酒精含量大于等于中位数的样本
high_alcohol =df[df.alcohol >= 10.3]
# 确保这些查询中的每个样本只出现一次
num_samples = df.shape[0]
num_samples == low_alcohol['quality'].count() + high_alcohol['quality'].count() # 应为真
# 获取低酒精含量组和高酒精含量组的平均质量评分
low_alcohol.quality.mean(), high_alcohol.quality.mean()
# 获取残留糖分的中位数
df.residual_sugar.median()
# 选择残留糖分小于中位数的样本
low_sugar =df[df.residual_sugar < 3]
# 选择残留糖分大于等于中位数的样本
high_sugar =df[df.residual_sugar >= 3]
# 确保这些查询中的每个样本只出现一次
num_samples == low_sugar['quality'].count() + high_sugar['quality'].count() # 应为真
# 获取低糖分组和高糖分组的平均质量评分
low_sugar.quality.mean(), high_sugar.quality.mean()
colors=['red','white']
wine_df.groupby('color')['quality'].mean().plot(kkind='bar',title='ceshi1',colors=['red','white'],alpha=.7)
引入sns matplotlib
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
...
...
...
colors=['red','white']
color_means=wine_df.groupby('color')['quality'].mean()
color_means.plot(kkind='bar',title='ceshi1',colors=colors,alpha=.7)
plt.xlabel("colors",fontsize=18)
plt.ylabel("colors",fontsize=18)
counts= wine_df.groupby(['quality','color']).count()['pH']
counts
totals=wine_df.groupby('color').count()['pH']
proportions = counts /totals
proportions.plot(kind='bar',title='ceshi1',colors=colors,alpha=.7)
import matplotlib.pyplot as plt
% matplotlib inline
plt.bar([1, 2, 3], [224, 620, 425]);
# 绘制条柱
plt.bar([1, 2, 3], [224, 620, 425])
# 为 x 轴指定刻度标签及其标签
plt.xticks([1, 2, 3], ['a', 'b', 'c']);
# 用 x 轴的刻度标签绘制条柱
plt.bar([1, 2, 3], [224, 620, 425], tick_label=['a', 'b', 'c']);
plt.bar([1, 2, 3], [224, 620, 425], tick_label=['a', 'b', 'c'])
plt.title('Some Title')
plt.xlabel('Some X Label')
plt.ylabel('Some Y Label');
# 用查询功能选择每个组，并获取其平均质量
median = df['alcohol'].median()
low = df.query('alcohol < {}'.format(median))
high = df.query('alcohol >= {}'.format(median))
mean_quality_low = low['quality'].mean()
mean_quality_high = high['quality'].mean()
# 用合适的标签创建柱状图
locations = [1, 2]
heights = [mean_quality_low, mean_quality_high]
labels = ['Low', 'High']
plt.bar(locations, heights, tick_label=labels)
plt.title('Average Quality Ratings by Alcohol Content')
plt.xlabel('Alcohol Content')
plt.ylabel('Average Quality Rating');
用 Matplotlib 绘制酒的类型和质量视图
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
% matplotlib inline
import seaborn as sns
sns.set_style('darkgrid')
wine_df = pd.read_csv('winequality_edited.csv')
# 获取每个等级和颜色的数量
color_counts = wine_df.groupby(['color', 'quality']).count()['pH']
color_counts
# 获取每个颜色的总数
color_totals = wine_df.groupby('color').count()['pH']
color_totals
# 将红葡萄酒等级数量除以红葡萄酒样本总数，获取比例
red_proportions = color_counts['red'] / color_totals['red']
red_proportions
# 将白葡萄酒等级数量除以白葡萄酒样本总数，获取比例
white_proportions = color_counts['white'] / color_totals['white']
white_proportions
ind = np.arange(len(red_proportions)) # 组的 x 坐标位置
width = 0.35 # 条柱的宽度
# 绘制条柱
red_bars = plt.bar(ind, red_proportions, width, color='r', alpha=.7, label='Red Wine')
white_bars = plt.bar(ind + width, white_proportions, width, color='w', alpha=.7, label='White Wine')
# 标题和标签
plt.ylabel('Proportion')
plt.xlabel('Quality')
plt.title('Proportion by Wine Color and Quality')
locations = ind + width / 2 # x 坐标刻度位置
labels = ['3', '4', '5', '6', '7', '8', '9'] # x 坐标刻度标签
plt.xticks(locations, labels)
# 图例
plt.legend()
red_proportions['9'] = 0
red_proportions