23.03.26_Pandas

1. pandas常用数据类型：
   1） Series 一维，带标签数组
   2） DataFrame 二维，Series容器
2. Series：
   1）创建
   
   
   2）索引和值：
   
3. pandas读取外部数据：
   1）csv文件：

import pandas as pd

df = pd.read_csv("./dogNames2.csv")
print(df)

2）mongodb：

import pandas as pd
from pymongo import MongoClient

client = MongoClient()
collection = client["douban"]["tv1"] # Won't work since there's no data in Mongodb
data = collection.find()

data_list = [] # 字典数组
for i in data:
    temp = {} # 每个字典
    temp["info"]= i["info"]
    temp["rating_count"] = i["rating"]["count"]
    temp["rating_value"] = i["rating"]["value"]
    temp["title"] = i["title"]
    temp["country"] = i["tv_category"]
    temp["directors"] = i["directors"]
    temp["actors"] = i['actors']
    data_list.append(temp)

df = pd.DataFrame(data_list)
print(df)

4. DataFrame：
   1）创建：

import numpy
import pandas as pd
# 直接创建
t = pd.DataFrame(numpy.arange(12).reshape(3,4),index=list("abc"),columns=list("WXYZ"))
print(t)

# 使用字典
d1 = {
    "name":["Alex","John"],
    "age":[20,32],
    "tel":[10084, 213213],
}
t1 = pd.DataFrame(d1)
print(t1)

# 使用字典的列表
d2 = [{"name":"Luigi","age":34,"tel":8394},
      {"name":"Yovanne","age":12},
      {"name":"Noan","tel":132134}
      ]
t2 = pd.DataFrame(d2)
print(t2)

2）常用方法：

3) 排序：

@desc:找出次数最高的前几个狗名字
"""
import pandas as pd

data = pd.read_csv("dogNames2.csv")

# 排序方法
data = data.sort_values(by="Count_AnimalName",ascending=False)

print(data.head(20)["Row_Labels"])

4）取行或列：



5）布尔索引：


6）字符串方法：

5. 处理缺失数据：

6. pandas常用统计方法：

@desc:2006年到2016年1000部最流行的电影数据，我们想知道这些电影数据中评分的平均分，导演的人数等信息
"""
import numpy
import pandas as pd

file_path = "./IMDB-Movie-Data.csv"
data = pd.read_csv(file_path)

print(data.info())

# 获取平均分
print(round(data["Rating"].mean(),2))

# 导演人数
print(len(data["Director"].unique()))

# 演员人数
actors_list = data["Actors"].str.split(", ").tolist()
print(actors_list)
actors_num = len(set([actor for actors in actors_list for actor in actors]))
print(actors_num)

对于这一组电影数据，如果我们想rating，runtime的分布情况，应该如何呈现数据？

@desc: draw the historgram of runtime
"""

import pandas as pd
from matplotlib import pyplot as plt

file_path = "./IMDB-Movie-Data.csv"
data = pd.read_csv(file_path)
print(data.info())

runtime_data = data["Runtime (Minutes)"].values

max_runtime = runtime_data.max()
min_runtime = runtime_data.min()

print(max_runtime-min_runtime)
num_bin = (max_runtime-min_runtime) // 5

plt.figure(figsize=(20,8),dpi=80)
plt.hist(runtime_data,num_bin)

plt.xticks(range(min_runtime,max_runtime+5,5))

plt.show()

@desc: draw the historgram of rating
"""

import pandas as pd
from matplotlib import pyplot as plt

file_path = "./IMDB-Movie-Data.csv"
data = pd.read_csv(file_path)

rating_data = data["Rating"].values

max_rating = rating_data.max()
min_rating = rating_data.min()

# 计算组数(使组数和刻度一致，需要手动调整）
bins = [1.9]
bin = 1.9
while bin <= max_rating:
    bin += 0.5
    bins.append(bin)
print(bins)

plt.figure(figsize=(20,8),dpi=80)
plt.hist(rating_data,bins=bins) # 自定义bins

# xticks for floating numbers
_x = [min_rating]
i = min_rating
while i <= max_rating:
    i += 0.5
    _x.append(i)
print(_x)
plt.xticks(_x)

plt.show()