def no_correlation(df: DataFrame) -> DataFrame:
"""
Counts 'nie' word occurrence in descriptions.
Adds result to the no_count column and returns
correlation matrix.
:param df:DataFrame
:return:DataFrame correlation matrix
"""
df['no_count'] = 0
for i, row in df.iterrows():
no_count = 0
desc_list = row.description.split(' ')
for word in desc_list:
if word.lower() == 'nie':
no_count += 1
df.at[i, 'no_count'] = no_count
return df.corr(method='pearson')
def parametercorr(conv):
re_conv = np.reshape(conv, (-1, conv.shape[-2], conv.shape[-1]))
re_conv = np.abs(re_conv)
re_conv = np.sum(re_conv, axis=0)
data = DataFrame(re_conv)
relation = data.corr()
length = relation.shape[0]
final_cols = []
del_cols = []
for i in range(length):
if relation.columns[i] not in del_cols:
final_cols.append(relation.columns[i])
for j in range(i + 1, length):
if (relation.iloc[i, j] > 0.85) and (relation.columns[j]
not in del_cols):
del_cols.append(relation.columns[j])
for i in range(len(final_cols)):
data[final_cols[i]] = 0
nddata = np.array(data)
data_list = nddata.tolist()
return data_list, len(del_cols)
print(count_violations, count_violations.sum(), np.array(result_list).shape[0])
criticality = 0
for i in range(len(count_violations)):
criticality += count_violations[i] * (127 - i) / 127
print(criticality / count_violations.sum())
category = 0
for i in range(len(count_violations)):
if count_violations[i] > 0:
category += 1
print(category, category / 128)
sns.set_style("darkgrid")
data_result = DataFrame(result_list)
data_result.rename(columns={
0: 'a',
1: 'b',
2: 'c',
3: 'd',
4: 'e',
5: 'f',
6: 'g'
},
inplace=True) #注意这里0和1都不是字符串
data_result.dropna(axis=0, how='any')
print(data_result.corr())
sampledata=[]#样本库
for i in range(len(value)):
for j in range(length[i]):
for z in range(8,9):#只用了通道8的信号
xinhao=value[name[i]][str(j)][z].tolist() #循环取通道信号
te1=tezhengliangtiqu.tezhengti(xinhao) #某一通道信号的特征量提取
te1=np.append(te1,int(i))#i为标签，0-4与name对应
if not len(sampledata):
sampledata=[te1.tolist()]
else:
sampledata=np.concatenate((sampledata,[te1.tolist()]),axis=0)
#相关度计算
from pandas.core.frame import DataFrame
samp=DataFrame(sampledata[:,0:-1])
print(samp.corr())
samp.corr().to_excel('test1.xlsx', index=True, header=None)
markers=('s','x','o','^','v')
colors=('red','blue','lightgreen','gray','cyan')
i=2
for idx,c1 in enumerate(np.unique(y)):
tezheng1=sampledata[sampledata[:,-1]==c1,0]
plt.plot(range(len(tezheng1)),tezheng1,alpha=0.8,c=colors[idx],marker=markers[idx],label=c1)
plt.legend(['normal','dianshi','mosun','duanchi'],loc='best')
plt.show()
plt.scatter(range,sampledata[:,0])
svmxunlian.svmxunlian(sampledata,length)
'Kill_event': atd.team_kill_event,
#'All_event': atd.team_event,
#'Dx':atd.dxdy[0],
#'Dy':atd.dxdy[1],
#'C':C_data,
'Max_eig': graph_max_eig_data,
'Short_path': short_path_data,
#'Ac':Ac_data,
'Degree': degree_data,
'Closeness': closeness_data,
#'Betweenness':betweenness_data,
#'Eigenvector':eigenvector_data,
}
data = DataFrame(pandata) #将字典转换成为数据框
# 相关性分析结束
corr_data = data.corr() #可以使用参数 'pearson', 'kendall', 'spearman'
print("表5(注意选出几列即可不用全写上去)")
print(corr_data)
# 小世界网络指数
ws = nx.watts_strogatz_graph(50, 5, 0.5)
A = np.array(nx.adjacency_matrix(ws).todense()) # 对应的邻接矩阵
L_rand = nx.average_shortest_path_length(ws, weight="weight")
C_rand = C(A)
# L_avg = pandata['Short_path'][team_P]
zo = ad2zo(Hc_team_P) #0-1矩阵
zgraph = zo2graph(team_use_hero[team_P], zo) #0-1图
L_avg = avg_short_path_length(zgraph)
# C_avg = pandata['C'][team_P]
C_avg = C(zo)
s = (C_avg / C_rand) / (L_avg / L_rand)
print("表一协作网络平均路径长度:" + str(L_avg) + "聚集系数:" + str(C_avg) + "\n")
plt.close()
for col in columns_name:
df[col].plot.box()
plt.savefig("outs\\boxes\\{}.png".format(col))
plt.close()
for col in columns_name:
result = sql_manager.crs.execute((
"select distinct {},count({}) from information group by {}".format(
col, col, col))).fetchall()
counts = [x[1] for x in result]
attr = [x[0] for x in result]
fig1, ax1 = plt.subplots()
ax1.pie(counts,
labels=attr,
autopct='%1.1f%%',
shadow=True,
startangle=90)
ax1.axis('equal'
) # Equal aspect ratio ensures that pie is drawn as a circle.
plt.savefig("outs\\pie_plots\\{}.png".format(col))
plt.close()
corrMatrix = df.corr()
sn.heatmap(corrMatrix, annot=True)
plt.show()
# plt.savefig("outs\\corr_table.pdf",dpi=400)
plt.close()
