2020-09-22

口袋妖怪数据集探索

数据集下载

#服务器命令
!wget -O pokemon_data.csv https://pai-public-data.oss-cn-beijing.aliyuncs.com/pokemon/pokemon.csv

!pip install seaborn --user -q

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

df = pd.read_csv("./pokemon_data.csv")

df.head()

df.info()

# 计算出每个特征有多少百分比是缺失的
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)

# 查看各代口袋妖怪的数量
df['generation'].value_counts().sort_values(ascending=False).plot.bar()

# 查看每个系口袋妖怪的数量
df['type1'].value_counts().sort_values(ascending=True).plot.barh()

# 相关性热力图分析
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)

interested = ['hp','attack','defense','sp_attack','sp_defense','speed']
sns.pairplot(df[interested])

# 通过相关性分析heatmap分析五个基础属性
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")

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

# 种族值分布
total_stats = df.total_stats
plt.hist(total_stats,bins=35)
plt.xlabel('total_stats')
plt.ylabel('Frequency')

plt.subplots(figsize=(20,12))
ax = sns.violinplot(x="type1", y="total_stats",
                    data=df, palette="muted")

# 种族值大于570的，但是不是神兽的
df[(df.total_stats >= 570) & (df.is_legendary == 0)]['name'].head(10)

其他有意思的分析

sns.jointplot("base_egg_steps", "experience_growth", data=df, size=5, ratio=3, color="g")

sns.jointplot("attack", "hp", data=df, kind="kde")

# 双系宝可梦数量统计
plt.subplots(figsize=(10, 10))

sns.heatmap(
    df[df['type2']!='None'].groupby(['type1', 'type2']).size().unstack(),
    linewidths=1,
    annot=True,
    cmap="Blues"
)

plt.xticks(rotation=35)
plt.show()