import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

filename = 'eva5_4__17.csv'
result = pd.read_csv(filename)
result.head()

y_train = result.label
y_train_pred = result.recommend_mode

from sklearn.metrics import confusion_matrix
import itertools
from sklearn import metrics
def plot_confusion_matrix(cm, classes,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    """
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=0)
    plt.yticks(tick_marks, classes)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

# Compute confusion matrix
cnf_matrix = confusion_matrix(y_train,y_train_pred)
np.set_printoptions(precision=2)

print('分类准确率是 ',metrics.accuracy_score(y_train, y_train_pred))
print("Recall metric in the testing dataset: ", metrics.recall_score(y_train,y_train_pred))

# Plot non-normalized confusion matrix
class_names = range(1,12)
plt.figure(figsize=(16,9))
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Confusion matrix')
# plt.savefig('conf_mx_5_4_17.png', bbox_inches='tight')
plt.savefig('twx_valPredict0508.png', bbox_inches='tight')
plt.show()

classification = []
for i in range(1,12):
    a = 'mode'+str(i)
    classification.append(a)

print(metrics.classification_report(y_train,y_train_pred,target_names=classification))

print(classification)

for i in range(1,12):
    print('mode %d 的精确率为 %f, 召回率为 %f'%(i,np.divide(cnf_matrix[i-1,i-1],np.sum(cnf_matrix[0:12,i-1]))
                                                   ,np.divide(cnf_matrix[i-1,i-1],np.sum(cnf_matrix[i-1,0:12]))))
    print('\t预测错误 %d, 自身分类错误 %d'%(np.subtract(np.sum(cnf_matrix[0:12,i-1]),cnf_matrix[i-1,i-1])
                                                     ,np.subtract(np.sum(cnf_matrix[i-1,0:12]),cnf_matrix[i-1,i-1])))

for i in range(1,12):
#     TrueData = 
    print(cnf_matrix[i-1,i-1])
#     PredDate = 
#     cnf_matrix[range(12),i]

# import matplotlib.pyplot as plt
# import numpy as np

# plt.rcParams['font.sans-serif'] = ['SimHei'] #（替换sans-serif字体）
# plt.rcParams['axes.unicode_minus'] = False   #（解决坐标轴负数的负号显示问题）


# TrueData = cnf_matrix[i,range(12)]
# PredDate = cnf_matrix[range(12),i]
# labels =["mode0","mode1","mode2","mode3","mode4","mode5","mode6","mode7","mode8","mode9","mode10","mode11"]


# #ax2 = fig.add_subplot(222) #2X2 中的第一个子图
# #bar(left, height, width, color, align, yerr)函数：绘制柱形图。
# # left为x轴的位置序列，一般采用arange函数产生一个序列；
# # height为y轴的数值序列，也就是柱形图的高度，一般就是我们需要展示的数据；
# # width为柱形图的宽度，一般这是为1即可；color为柱形图填充的颜色;
# # align设置plt.xticks()函数中的标签的位置；
# # yerr让柱形图的顶端空出一部分。
# # color设置柱状的颜色
# # alpha 设置柱状填充颜色的透明度 大于0 小于等于1
# # linewidth 线条的宽度

# #设置各种参数
# xlocation =  np.linspace(1, len(job_data) * 0.6, len(job_data)) #len(data个序列)
# print(xlocation)
# height01 = job_data
# height02 = how_many
# width = 0.2
# color01='darkgoldenrod'
# color02 = 'seagreen'

# # 画柱状图
# ax1 = plt.figure('十大热门城市招聘排行',figsize=(10,6)) #指定了图的名称 和画布的大小
# ax1.tight_layout()
# # ax1 = fig.add_subplot(221) #2X2 中的第一个子图
# plt.title('十大热门城市招聘排行', fontsize=15) # 添加图标题
# #画图
# rects01 = plt.bar(xlocation, height01, width = 0.2, color=color01,linewidth=1,alpha=0.8)
# rects02 = plt.bar(xlocation+0.2,height02 ,width = 0.2, color=color02,linewidth=1,alpha=0.8)
# #添加x轴标签
# plt.xticks(xlocation+0.15,labels, fontsize=12 ,rotation = 20)  # 横坐标轴标签 rotation x轴标签旋转的角度
# # 横纵坐标分别代表什么
# plt.xlabel(u'地点', fontsize=15, labelpad=10)
# plt.ylabel(u'职位数量', fontsize=15, labelpad=10)
# #图例
# plt.legend((rects01,rects02),( u'职位数量',u'招聘人数'), fontsize=15)  # 图例
# # 添加数据标签
# for r1,r2 ,amount01,amount02 in zip(rects01, rects02,job_data,how_many):
#         h01 = r1.get_height()
#         h02 = r2.get_height()
#         plt.text(r1.get_x(), h01, amount01, fontsize=13, va='bottom')  # 添加职位数量标签
#         plt.text(r2.get_x(), h02 , amount02, fontsize=13, va='bottom')  # 添加招聘人数
        
# plt.show()

# import 
profile1 = []
for i in range(67):
    string='p'+str(i-1)
    profile1=profile1.extend(string)

profile1

test_queries = pd.read_csv('test_queries.csv')

train_queries = pd.read_csv('train_queries.csv')

55025/94357

test_pid = list(test_queries['pid'][test_queries['pid'].notna()])

train_pid = list(train_queries['pid'][train_queries['pid'].notna()])

i = 0
for pid in test_pid:
    if pid in train_pid:
        i+=1

print(i）

test_queries['pid'].isna().sum()
# test_queries['pid'].count()
# len(test_queries['pid'])

twx_eval = pd.read_csv('twx_valPredict0508.csv')
twx_eval.head()

twx_eval.predict.unique()

y_train = twx_eval.true
y_train_pred = twx_eval.predict

!pip install jovian --upgrade

import jovian