导入库
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
import plotly_express as px
import plotly.graph_objects as go
数据基本信息
data = pd.read_csv("AppleStore.csv", index_col=0)
data.head()
image.png
# 整体大小
data.shape
image.png
# 缺失值
data.isnull().sum()
image.png
# 字段类型
data.dtypes
image.png
# 描述信息
data.describe()
image.png
APP信息统计
# 免费的APP数量
sum(data.price==0)
image.png
# 价格超过50$的APP数量，价格大于50$即表示为：超贵
sum(data.price >= 50)
image.png
# 价格超过50$的比例
sum((data.price > 50) / len(data.price) * 100)
image.png
sum(data.price >= 50) / len(data) * 100
image.png
# 立群数据
# 价格超过50$的APP信息
outlier = data[data.price > 50][["track_name", "price", "prime_genre", "user_rating"]]
outlier
image.png
免费APP
freeapps = data[data["price"] == 0]
freeapps.head()
image.png
正常区间的APP
# 取数
paidapps = data[(data["price"] > 0) & (data.price < 50)]
print("max_price:", max(paidapps.price))
print("min_price:", min(paidapps.price))
image.png
# 价格分布
plt.style.use("fivethirtyeight")
plt.figure(figsize=(12, 10))
# 绘制直方图
plt.subplot(2, 1, 1)
plt.hist(paidapps.price, log=True)
# 标题和label值
plt.title("Price distribution of apps (Log scale)")
plt.ylabel("Frequency Log scale")
plt.xlabel("Price Distributions in ($)")
# 绘制stripplot(分布散点图)
plt.subplot(2, 1, 2)
plt.title("Visual Price distribution")
sns.stripplot(data=paidapps,
x="price",
jitter=True, #当数据点重合较多时，用该参数做调整
size=6)
plt.show()
image.png
1.随着价格的上涨，付费应用的数量呈现指数级的下降
2.很少应用的价格超过30刀；因此，尽量保持价格在30以下
category对价格分布的影响
data.columns
image.png
# 种类及数目
data["prime_genre"].value_counts()
image.png
# 显示前5个种类
yrange = [0, 25]
fsize = 15
plt.figure(figsize=(12, 10))
plt.subplot(5, 1, 1)
plt.xlim(yrange)
games = paidapps[paidapps["prime_genre"] == "Games"]
sns.stripplot(data=games,
x="price",
jitter=True,
size=6,
color="#eb5e66")
plt.title("Games", fontsize=fsize)
plt.xlabel("")
plt.subplot(5, 1, 2)
plt.xlim(yrange)
ent = paidapps[paidapps["prime_genre"] == "Entertainment"]
sns.stripplot(data=ent,
x="price",
jitter=True,
size=6,
color="#ff8300")
plt.title("Entertainment", fontsize=fsize)
plt.xlabel("")
plt.subplot(5, 1, 3)
plt.xlim(yrange)
edu = paidapps[paidapps.prime_genre == "Education"]
sns.stripplot(data=edu,
x="price",
jitter=True,
size=6,
color="#20B2AA")
plt.title("Education", fontsize=fsize)
plt.xlabel("")
plt.subplot(5, 1, 4)
plt.xlim(yrange)
pv = paidapps[paidapps.prime_genre == "Photo & Video"]
sns.stripplot(data=pv,
x="price",
jitter=True,
size=6,
color="#b84efd")
plt.title("Photo & Video", fontsize=fsize)
plt.xlabel("")
plt.subplot(5, 1, 5)
plt.xlim(yrange)
ut = paidapps[paidapps.prime_genre == "Utilities"]
sns.stripplot(data=pv,
x="price",
jitter=True,
size=6,
color="#084cfd")
plt.title("Utilities", fontsize=fsize)
plt.xlabel("")
image.png
1.Games游戏类的apps价格相对高且分布更广，直到25美元
2.Entertainment娱乐类的apps价格相对较低
Paid apps Vs Free apps
# 付费APP和免费APPA之间的比较
# app的种类
categories = data["prime_genre"].value_counts()
categories
image.png
len(categories)
image.png
# 选择前4个
s = categories.index[:4]
s
image.png
def categ(x):
if x in s:
return x
else:
return "Others"
data["broad_genre"] = data["prime_genre"].apply(categ)
data.head()
image.png
# 统计免费和付费APP下的种类数
# 免费
data[data.price==0].broad_genre.value_counts()
image.png
# 免费APP
free = data[data.price==0].broad_genre.value_counts().sort_index().to_frame()
free
image.png
# 付费
paid = data[data.price > 0].broad_genre.value_counts().sort_index().to_frame()
paid
image.png
# 全部
total = data.broad_genre.value_counts().sort_index().to_frame()
total
image.png
# 将两个数据合并起来
free.columns = ["free"]
paid.columns = ["paid"]
total.columns = ["total"]
free
image.png
# 统计量对比
dist = free.join(paid).join(total)
# 另一种写法
dist = pd.concat([paid, free, total], axis=1)
dist
image.png
# 生成比例
dist["paid_per"] = dist.paid / dist.total * 100
dist["free_per"] = dist.free / dist.total * 100
dist
image.png
# 高亮显示最大值
dist.style.highlight_max()
image.png
1.Games相关的APP是最多的，不管是paid还是free
2.从付费占比来看，Education教育类型占比最大
3.从免费占比来看，Entertainment娱乐类型的占比最大
付费和免费的占比
# 生成数据
# 分组对比付费和免费的占比
list_free = dist.free_per.tolist()
list_free
image.png
# 列表转成元组
tuple_free = tuple(list_free)
tuple_paidapps = tuple(dist.paid_per.tolist())
# 柱状图
plt.figure(figsize=(12, 8))
N = 5
ind = np.arange(N)
width = 0.56 #两个柱子间的宽度
p1 = plt.bar(ind, tuple_free, width, color="#45cea2")
p2 = plt.bar(ind, tuple_paidapps, width, bottom=tuple_free, color="#fdd400")
plt.xticks(ind, tuple(dist.index.tolist()))
plt.legend((p1[0], p2[0]), ("free", "paid"))
plt.show()
image.png
# 饼图
pies = dist[["free_per", "paid_per"]]
pies.columns = ["free %", "paid %"]
pies
image.png
plt.figure(figsize=(15, 8))
pies.T.plot.pie(subplots=True, #显示子图
figsize=(20, 4), #大小
colors=["#45cea2", "#fad470"]) #颜色
plt.show()
image.png
1.在教育类的APP中，付费paid的占比是很高的
2.相反的，在娱乐类的APP中，免费free的占比是很高的
付费APP真的足够好吗？
# 价格分类
data["category"] = data["price"].apply(lambda x: "Paid" if x > 0 else "Free")
data.head()
image.png
# 小提琴图
plt.figure(figsize=(15, 8))
plt.style.use("fast")
plt.ylim([0, 5])
plt.title("Distribution of User ratings")
sns.violinplot(data=data,
y="user_rating",
x="broad_genre",
hue="category",
vertical=True, #垂直显示
kde=False,
split=True, #同个类别的小提琴图一起显示
linewidth=2,
scale="count",
palette=["#fdd470", "#45cea2"])
plt.xlabel(" ")
plt.ylabel("Rating(0-5)")
plt.show()
image.png
1.在Education类的APP中，paid的占比是明显高于free；其次是Photo & Video
2.Entertainment娱乐的APP，free占比高于paid；且整体的占比分布更为宽
plt.figure(figsize=(15, 8))
plt.style.use("fast")
plt.ylim([0, 5])
plt.title("Distribution of User ratings")
sns.violinplot(data=data,
y="user_rating",
x="broad_genre",
hue="category",
vertical=True, #垂直显示
kde=False,
split=False, #同个类别的小提琴图一起显示
linewidth=2,
scale="count",
palette=["#fdd470", "#45cea2"])
plt.xlabel(" ")
plt.ylabel("Rating(0-5)")
plt.show()
image.png
size和price关系
sns.color_palette("husl", 8)
sns.set_style("whitegrid")
flatui = ["#9b59b6", "#3498db", "#95a5a6", "#e74c3c", "#34495e", "#2ecc71"]
data["MB"] = data.size_bytes.apply(lambda x: x/1048576)
# 挑选区间的数据
paidapps_regression = data[((data.price < 30) & (data.price > 0))]
sns.lmplot(data=paidapps_regression,
x="MB",
y="price",
height=4,
aspect=2,
col_wrap=2,
hue="broad_genre",
col="broad_genre",
fit_reg=False,
palette=sns.color_palette("husl", 5))
plt.show()
image.png
# 使用Plotly实现
px.scatter(paidapps_regression,
x="MB",
y="price",
color="broad_genre",
facet_col="broad_genre",
facet_col_wrap=2)
image.png
# APP分类：是否可根据paid和free来划分
# 5种类型对比
# 设置颜色和大小
BlueOrangeWapang = ["#fc910d", "#fcb13e", "#239cd3", "#1674b1", "#ed6d50"]
plt.figure(figsize=(10, 10))
# 数据
label_names = data.broad_genre.value_counts().sort_index().index
size = data.broad_genre.value_counts().sort_index().tolist()
# 内嵌空白圈
my_circle = plt.Circle((0, 0), 0.5, color="white")
# 圆
plt.pie(size, labels=label_names, colors=BlueOrangeWapang)
p = plt.gcf()
p.gca().add_artist(my_circle)
plt.show()
image.png
# 使用Plotly实现
fig = px.pie(values=size,
names=label_names,
labels=label_names,
hole=0.5)
fig.update_traces(textposition="inside", textinfo="percent+label")
fig.show()
image.png
# 5种类型+是否付费
f = pd.DataFrame(index=np.arange(0, 10, 2),
data=dist.free.values,
columns=["num"])
p = pd.DataFrame(index=np.arange(1, 11, 2),
data=dist.paid.values,
columns=["num"])
final = pd.concat([f, p], names=["labels"]).sort_index()
final
image.png
final.num.tolist()
image.png
plt.figure(figsize=(20, 20))
group_names = data.broad_genre.value_counts().sort_index().index
group_size = data.broad_genre.value_counts().sort_index().tolist()
h = ["Free", "Paid"]
subgroup_names = 5*h
sub = ["#45cea2", "#fdd470"]
subcolors = 5*sub
subgroup_size = final.num.tolist()
# 外层
fig, ax = plt.subplots()
ax.axis("equal")
mypie, _ = ax.pie(group_size, radius=2.5, labels=group_names, colors=BlueOrangeWapang)
plt.setp(mypie, width=1.2, edgecolor="white")
# 内层
mypie2, _ = ax.pie(subgroup_size, radius=1.6, labels=subgroup_names, labeldistance=0.7, colors=subcolors)
plt.margins(0, 0)
plt.show()
image.png
# 使用Plotly实现
fig = px.sunburst(data,
path=["broad_genre", "category"],
values="MB")
fig.show()
image.png
来源：尤而小屋
