数据分析Numpy 作业 05 20200829

作业1

结合Matplotlib绘制各自的评论数量的图形，体现其评论数主要分布在哪个区间。

import numpy  as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator as mul   #重新设置坐标轴刻度

plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
#文字设置

def load_csv_to_array(filename:str):
    np_arr=np.loadtxt(filename,delimiter=',',skiprows=0,dtype=float)
    # print(np_arr)
    # print(type(np_arr))
    # print(np_arr.dtype)
    return np_arr
#加载csv文件

def comment_hist(ax_set,np_arr,graph_name,interval:int,color:str):
    np_data=np_arr[:,3]
    #获取评论列
    
    difference_com=np.max(np_data)-np.min(np_data)  #极差
    bins=round(difference_com/interval)				#组数
    print(bins)
    ax_set.set_xlabel('评论数')
    ax_set.set_ylabel('频数')
    ax_set.set_title(graph_name)
    x_major_locator = mul(interval)					#手动设置x轴的刻度间隔
    ax=plt.gca()
    ax.xaxis.set_major_locator (x_major_locator)	#设置x轴的主刻设置为x_major_locator的倍数
    plt.xticks(rotation=60)
    ax_set.hist(np_data,bins=bins,color=color, alpha=0.8, rwidth=0.8)

if __name__ == '__main__':
    fig,axes=plt.subplots(2,1,sharex=True,sharey=True,figsize=(14,8))
    ax1=fig.add_subplot(axes[0])
    ax2=fig.add_subplot(axes[1])
    np_arr = load_csv_to_array('GB_video_data_numbers.csv')
    comment_hist(ax1,np_arr,'GB_video_data_numbers',10000,'b')
    np_arr2 = load_csv_to_array('US_video_data_numbers.csv')
    comment_hist(ax2, np_arr2, 'US_video_data_numbers', 10000, 'b')
    plt.show()

作业2

绘制图形，分析英国的Youtube中视频的评论数与喜欢数的关系。

import numpy  as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator as mul

plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

def load_csv_to_array(filename:str):
    np_arr=np.loadtxt(filename,delimiter=',',skiprows=0,dtype=float)
    return np_arr

def links_comments_to_likes(np_arr):
    plt.figure(figsize=(14,8))
    comment_list=np_arr[:,3]
    likes_list=np_arr[:,1]
    x_major_locator = mul(20000)
    ax=plt.gca()
    ax.xaxis.set_major_locator (x_major_locator)
    ax.set_xlabel('评论数')
    ax.set_ylabel('喜欢数')
    ax.set_xlim ( np.min(comment_list), np.max(comment_list) )
    plt.xticks(rotation=60)
    plt.scatter(comment_list,likes_list, marker = 'x',color = 'red',s=20)
    plt.show()
    
np_arr = load_csv_to_array('GB_video_data_numbers.csv')
links_comments_to_likes(np_arr)

作业3

望将两个国家的数据拼接一起来研究分析。
• 拼接全为0的数组标识为英国
• 拼接全为1的数组标识为美国
• 将两个国家的数据拼接

import numpy as np

def load_csv_to_array(filename:str):
    np_arr=np.loadtxt(filename,delimiter=',',skiprows=0,dtype=float)
    # print(np_arr)
    # print(type(np_arr))
    # print(np_arr.dtype)
    return np_arr

def hstack_col(np_arr,data_col):
    if data_col == 0:
        col_0 = np.zeros ( (np_arr.shape[0], 1), dtype=int )
    elif data_col == 1:
        col_0 = np.ones ( (np_arr.shape[0], 1), dtype=int )
    else:
        print('data_col 的值必须为0或1')
        return np.array([])
    new_np_arr = np.hstack((col_0,np_arr))
    return new_np_arr

if __name__ == '__main__':
    np_eng_arr = load_csv_to_array ( 'GB_video_data_numbers.csv' )

    if np_eng_arr.size != 0:
        new_np_eng_arr = hstack_col ( np_eng_arr, 0)

    np_us_arr = load_csv_to_array ( 'US_video_data_numbers.csv' )
    if np_us_arr.size != 0 :
        new_np_us_arr = hstack_col ( np_us_arr, 1 )

    if new_np_en_arr.size != 0 and new_np_us_arr.size != 0:
        np_eng_and_us_arr = np.vstack ( (new_np_eng_arr, new_np_us_arr) )
        print(np_eng_and_us_arr)