scatter

jackzhenguo · jackzhenguo · commit a36b777c8c93 · 2019-12-10T07:56:56.000+08:00
diff --git a/README.md b/README.md
@@ -670,6 +670,44 @@ heatmap_plot = sns.heatmap(data, center=0, cmap='gist_rainbow')
 plt.show()
 ```
 ![热力图](./img/heatmap.png)
+2 散点图
+```python
+import numpy as np
+import pandas as pd
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+
+# 版本检查
+print(mpl.__version__)  #> 3.0.0
+
+
+# 导入数据集
+midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")
+
+
+# midwest['category']分类，颜色设置为与其一样多
+categories = np.unique(midwest['category'])
+colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))]
+
+# 每个分类plot
+plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')
+
+for i, category in enumerate(categories):
+    plt.scatter('area', 'poptotal', 
+                data=midwest.loc[midwest.category==category, :], 
+                s=20, c=colors[i], label=str(category))
+
+# 修改x轴,y轴坐标系尺寸区间
+plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000),
+              xlabel='Area', ylabel='Population')
+
+plt.xticks(fontsize=12)
+plt.yticks(fontsize=12)
+plt.title("Midwest Area vs Population", fontsize=22)
+plt.legend(fontsize=12)    
+plt.show()    
+```
+![散点图](./img/scatter-plt.png)
 
 #### 十三、PyQt
 
diff --git a/img/scatter-plt.png b/img/scatter-plt.png
diff --git a/md/README.md b/md/README.md
@@ -76,6 +76,7 @@
 2. [turtle绘制漫天雪花](turtle绘制漫天雪花.md)
 3. [4种不同颜色的色块，它们的颜色真的不同吗？](4种不同颜色的色块，它们的颜色真的不同吗？.md)
 4. [词频云图](词频云图.md)
+5. [散点图](散点图.md)
 
 
 #### 九、生成器
diff --git a/md/散点图.md b/md/散点图.md
@@ -0,0 +1,37 @@
+```python
+import numpy as np
+import pandas as pd
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+
+# 版本检查
+print(mpl.__version__)  #> 3.0.0
+
+
+# 导入数据集
+midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")
+
+
+# midwest['category']分类，颜色设置为与其一样多
+categories = np.unique(midwest['category'])
+colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))]
+
+# 每个分类plot
+plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')
+
+for i, category in enumerate(categories):
+    plt.scatter('area', 'poptotal', 
+                data=midwest.loc[midwest.category==category, :], 
+                s=20, c=colors[i], label=str(category))
+
+# 修改x轴,y轴坐标系尺寸区间
+plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000),
+              xlabel='Area', ylabel='Population')
+
+plt.xticks(fontsize=12)
+plt.yticks(fontsize=12)
+plt.title("Midwest Area vs Population", fontsize=22)
+plt.legend(fontsize=12)    
+plt.show()    
+
+```
diff --git a/src/scatter.py b/src/scatter.py
@@ -0,0 +1,34 @@
+import numpy as np
+import pandas as pd
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+
+# 版本检查
+print(mpl.__version__)  #> 3.0.0
+
+
+# 导入数据集
+midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")
+
+
+# midwest['category']分类，颜色设置为与其一样多
+categories = np.unique(midwest['category'])
+colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))]
+
+# 每个分类plot
+plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')
+
+for i, category in enumerate(categories):
+    plt.scatter('area', 'poptotal', 
+                data=midwest.loc[midwest.category==category, :], 
+                s=20, c=colors[i], label=str(category))
+
+# 修改x轴,y轴坐标系尺寸区间
+plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000),
+              xlabel='Area', ylabel='Population')
+
+plt.xticks(fontsize=12)
+plt.yticks(fontsize=12)
+plt.title("Midwest Area vs Population", fontsize=22)
+plt.legend(fontsize=12)    
+plt.show()    
