口袋妖怪数据集探索
数据集下载
!wget -O pokemon_data.csv https://pai-public-data.oss-cn-beijing.aliyuncs.com/pokemon/pokemon.csv
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
df = pd.read_csv("./pokemon_data.csv")
df.head()
查看数据
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915231024284.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
percent_missing = df.isnull().sum() * 100 / len(df)
missing_value_df = pd.DataFrame({
'column_name': df.columns,
'percent_missing': percent_missing
})
missing_value_df.sort_values(by='percent_missing', ascending=False).head(10)
percent_missing = df.isnull().sum() * 100 / len(df)
missing_value_df = pd.DataFrame({
'column_name': df.columns,
'percent_missing': percent_missing
})
missing_value_df.sort_values(by='percent_missing', ascending=False).head(10)
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915231242675.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
查看各代口袋妖怪的数量
df['generation'].value_counts().sort_values(ascending=False).plot.bar()
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915231345652.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
df['type1'].value_counts().sort_values(ascending=True).plot.barh()
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915231609889.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
plt.subplots(figsize=(20,15))
ax = plt.axes()
ax.set_title("Correlation Heatmap")
corr = df.corr()
sns.heatmap(corr,
xticklabels=corr.columns.values,
yticklabels=corr.columns.values)
![在这里插入图片描述](https://img-blog.csdnimg.cn/2020091523165180.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
interested = ['hp','attack','defense','sp_attack','sp_defense','speed']
sns.pairplot(df[interested])
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915231912222.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
plt.subplots(figsize=(10,8))
ax = plt.axes()
ax.set_title("Correlation Heatmap")
corr = df[interested].corr()
sns.heatmap(corr,
xticklabels=corr.columns.values,
yticklabels=corr.columns.values,
annot=True, fmt="f",cmap="YlGnBu")
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915232031215.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)
for c in interested:
df[c] = df[c].astype(float)
df = df.assign(total_stats = df[interested].sum(axis=1))
df[df.total_stats >= 525].shape
total_stats = df.total_stats
plt.hist(total_stats,bins=35)
plt.xlabel('total_stats')
plt.ylabel('Frequency')
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200915232147670.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzE0NDI5NQ==,size_16,color_FFFFFF,t_70#pic_center)