def tree_model(Xt, yt, Xv, yv, runRF, runGBRT, runGBRT2):
assert runRF + runGBRT + runGBRT2 == 1
if runRF:
model_name = "Random Forest"
max_depth = np.arange(2, 7, 2)
max_features = [Xt.shape[1] // 3]
# max_depth = np.arange(1, 3)
# max_features = [3, 5, 10]
param_grid = {'max_dep': max_depth, 'max_fea': max_features}
params = list(ParameterGrid(param_grid))
elif runGBRT or runGBRT2:
model_name = "Boosting Trees"
# boosting params
num_trees = [1000]
learning_rate = [0.01, 0.1]
# loss = ['huber']
# cart tree params
max_depth = [2, 4, 6]
param_grid = {
'num_trees': num_trees,
'max_dep': max_depth,
'lr': learning_rate
}
params = list(ParameterGrid(param_grid))
tis = time.time()
scores = []
model_list = []
for p in tqdm(params):
print(p)
if runRF:
# params = {
# 'colsample_bynode': 0.33,
# 'learning_rate': 1,
# 'max_depth': p['max_dep'],
# 'num_parallel_tree': 300,
# 'objective': 'reg:squarederror',
# 'subsample': 0.8,
# 'random_state': 0,
# 'tree_method': 'gpu_hist'
# }
# tree_m = xgb.XGBRFRegressor(n_estimators=300, max_depth=p['max_dep'], colsample_bynode=0.33
# random_state=0, tree_method='gpu_hist')
tree_m = RandomForestRegressor(n_estimators=300,
max_depth=p['max_dep'],
max_features=p['max_fea'],
min_samples_split=10,
random_state=0,
n_jobs=cpu_count() - 3)
tree_m.fit(Xt, yt.reshape(-1, ))
elif runGBRT:
tree_m = xgb.XGBRegressor(n_estimators=p['num_trees'],
max_depth=p['max_dep'],
learning_rate=p['lr'],
objective='reg:pseudohubererror',
random_state=0,
tree_method='gpu_hist')
callbacks = [
xgb.callback.EarlyStopping(rounds=0.1 * p['num_trees'],
save_best=True)
] # early_stopping_rounds=0.2*p['num_trees'],
tree_m = tree_m.fit(Xt,
yt.reshape(-1, ),
eval_set=[(Xv, yv.reshape(-1, ))],
verbose=False,
callbacks=callbacks)
print(f"gbrt best iter {tree_m.get_booster().best_iteration}",
"lowest error",
tree_m.get_booster().best_score)
# tree_m = GradientBoostingRegressor(max_depth=p['max_dep'], n_estimators=p['num_trees'],
# learning_rate=p['lr'],
# min_samples_split=10, loss=p['loss'], min_samples_leaf=10,
# subsample=p['subsample'], random_state=0)
elif runGBRT2:
tree_m = xgb.XGBRegressor(n_estimators=p['num_trees'],
max_depth=p['max_dep'],
learning_rate=p['lr'],
objective='reg:squarederror',
random_state=0,
tree_method='gpu_hist')
callbacks = [
xgb.callback.EarlyStopping(rounds=0.1 * p['num_trees'],
save_best=True)
] # early_stopping_rounds=0.2*p['num_trees'],
tree_m = tree_m.fit(Xt,
yt.reshape(-1, ),
eval_set=[(Xv, yv.reshape(-1, ))],
verbose=False,
callbacks=callbacks)
print(f"gbrt best iter {tree_m.get_booster().best_iteration}",
"lowest error",
tree_m.get_booster().best_score)
else:
raise NotImplementedError()
yv_hat = tree_m.predict(Xv).reshape(-1, 1)
score = cal_r2(yv, yv_hat)
print('params: ' + str(p) + '. CV r2-validation:' +
"{0:.3%}".format(score))
scores.append(score)
model_list.append(tree_m)
tic = time.time()
print(f"{model_name} train time: ", tic - tis)
best_p = params[np.argmax(scores)]
best_model = model_list[np.argmax(scores)]
logger.info('best params for rf: ' + str(best_p))
tree_m = best_model
return tree_m
def mainFunc(request):
#윤진씨
studentData = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/student.csv',
encoding='cp949')
# print(studentData.head(3))
# studentData.성적.value_counts()
# plot_div = sns.countplot(x='부모의학교만족도',data = studentData, hue='성적',palette='bright')
# fig = plt.gcf()
# fig.savefig('C:/work/py_sou/chartdb/mychart/static/image/chart.png', dpi=fig.dpi)
# df = studentData.groupby(['성적','부모의학교만족도'])
print(studentData.groupby(['성적'])['부모의학교만족도'].size())
fig = go.Figure(data=[
go.Bar(name='Good',
x=['H', 'L', 'M'],
y=studentData[studentData['부모의학교만족도'] == 'Good'].groupby(
['성적', '부모의학교만족도']).size(),
marker_color='#9bb1d6'),
go.Bar(name='Bad',
x=['H', 'L', 'M'],
y=studentData[studentData['부모의학교만족도'] == 'Bad'].groupby(
['성적', '부모의학교만족도']).size(),
marker_color='#a39bd6'),
])
# Change the bar mode
fig = fig.update_layout(barmode='group',
width=600,
height=600,
xaxis_title='성적',
yaxis_title='합계',
plot_bgcolor='rgba(0,0,0,0)',
paper_bgcolor='rgba(255,255,255,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18)) #데이터를 그룹화하여 표에 적용
# fig = px.bar(studentData, x='성적', y='부모의학교만족도', barmode='group',height=400)
plot_div = plot(fig, output_type='div')
#전공별 비율
fig2 = go.Figure(data=[
go.Pie(labels=[
'Arabic', 'Biology', 'Chemistry', 'English', 'French', 'Geology',
'History', 'IT', 'Math', 'Quran', 'Science', 'Spanish'
],
values=studentData.groupby(['전공']).size(),
textinfo='label+percent',
insidetextorientation='radial')
])
fig2 = fig2.update_layout(width=550,
height=500,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18),
showlegend=False)
pie_div = plot(fig2, output_type='div')
# print('룰루랄ㄹ라\n',studentData.groupby(['전공']).size())
#전공별 성적 비교----의미가 있는지 없는지 확인받기
majors = [
'Arabic', 'Biology', 'Chemistry', 'English', 'French', 'Geology',
'History', 'IT', 'Math', 'Quran', 'Science', 'Spanish'
]
fig3 = go.Figure()
fig3.add_trace(
go.Scatter(
x=studentData[studentData['성적'] == 'H'].groupby(['전공']).size(),
y=majors,
marker=dict(color="crimson", size=12),
mode="markers",
name="High",
))
fig3.add_trace(
go.Scatter(
x=studentData[studentData['성적'] == 'M'].groupby(['전공']).size(),
y=majors,
marker=dict(color="gold", size=12),
mode="markers",
name="Middle",
))
fig3.add_trace(
go.Scatter(
x=studentData[studentData['성적'] == 'L'].groupby(['전공']).size(),
y=majors,
marker=dict(color="black", size=12),
mode="markers",
name="Low",
))
fig3.update_layout(xaxis_title="학생수",
yaxis_title="전공",
width=700,
height=500,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
last_div = plot(fig3, output_type='div')
fig4 = go.Figure(data=[
go.Bar(name='7일이하',
x=['H', 'L', 'M'],
y=studentData[studentData['결석일수'] == 'Under-7'].groupby(
['성적']).size(),
text=studentData[studentData['결석일수'] == 'Under-7'].groupby(
['성적']).size(),
textposition='auto',
marker_color='rgb(204,153,153)'),
go.Bar(name='7일이상',
x=['H', 'L', 'M'],
y=studentData[studentData['결석일수'] == 'Above-7'].groupby(
['성적']).size(),
text=studentData[studentData['결석일수'] == 'Above-7'].groupby(
['성적']).size(),
textposition='auto',
marker_color='rgb(255,204,204)')
])
print(studentData[studentData['결석일수'] == 'Above-7'].groupby(['성적']).size())
fig4.update_layout(xaxis_title="성적",
yaxis_title="학생수",
width=600,
height=600,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
ab_plot = plot(fig4, output_type='div')
fig5 = px.scatter_matrix(studentData,
dimensions=["발표수", "과정반복수", "새공지사항확인수", "토론참여수"],
color="성적",
width=1200,
height=1000)
fig5.update_layout(width=800,
height=800,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
plot5_div = plot(fig5, output_type='div')
#찬규씨
plt.clf()
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/student.csv',
encoding='euc-kr')
data['성적'] = data['성적'].map({'H': 2, 'M': 1, 'L': 0})
# 국가별 성적 상.중.하 인원 분포도
df = pd.DataFrame({"국적": data['국적'], "성적": data['성적']})
df7 = pd.crosstab(df.성적, df.국적, margins=True)
# print(df7.columns)
for i in df7.columns:
df7[i] = df7[i].values / df7.loc['All', i] * 100
# result = df7['Egypt'].values / df7.loc['All', 'Egypt'] * 100
# print(result)
df7 = df7.drop(['All'])
fig8 = go.Figure(data=[
go.Bar(name='H',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df7.iloc[0, :17].values,
marker_color='rgb(152,105,247)'),
go.Bar(name='M',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df7.iloc[1, :17].values,
marker_color='rgb(247,152,105)'),
go.Bar(name='L',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df7.iloc[2, :17].values,
marker_color='rgb(105,247,152)'),
])
# Change the bar mode
fig8.update_layout(barmode='stack',
width=900,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
plot10_div = plot(fig8, output_type='div')
#--------- 국가별 성별 비율 그래프
df1 = pd.DataFrame({"국적": data['국적'], "성별": data['성별']})
print(df1)
df8 = pd.crosstab(df1.성별, df1.국적, margins=True)
print(df8)
df8 = df8.drop(['All'])
fig50 = go.Figure(data=[
go.Bar(name='M',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[0, :17].values,
marker_color='rgb(247,105,200)'),
go.Bar(name='F',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[1, :17].values,
marker_color='rgb(105,200,247)'),
])
# Change the bar mode
fig50.update_layout(barmode='stack',
width=900,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
cg_graph = plot(fig50, output_type='div')
fig9 = px.violin(data,
y="과정반복수",
x="결석일수",
color="성별",
box=True,
points="all",
hover_data=df.columns)
fig9.update_layout(width=1300)
fig9.update_layout(height=300)
plot11_div = plot(fig9, output_type='div')
# 3---1-1-1-1-1-1-1-1-1-1-1-1-1-1-1=-1--1-1-1-1-1-1--
df1 = pd.DataFrame({"결석일수": data['결석일수'], "새공지사항확인수": data['새공지사항확인수']})
print(df1)
df8 = pd.crosstab(df1.결석일수, df1.새공지사항확인수, margins=True)
print(df8)
df8 = df8.drop(['All'])
fig50 = go.Figure(data=[
go.Bar(name='Under-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[0, :17].values),
go.Bar(name='Above-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[1, :17].values),
])
# Change the bar mode
fig50.update_layout(xaxis_title='국적', yaxis_title='새공지사항확인수')
fig50.update_layout(width=700)
fig50.update_layout(height=250)
cg_graph7 = plot(fig50, output_type='div')
df1 = pd.DataFrame({"결석일수": data['결석일수'], "토론참여수": data['토론참여수']})
print(df1)
df8 = pd.crosstab(df1.결석일수, df1.토론참여수, margins=True)
print(df8)
df8 = df8.drop(['All'])
fig51 = go.Figure(data=[
go.Bar(name='Under-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[0, :17].values),
go.Bar(name='Above-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[1, :17].values),
])
# Change the bar mode
fig51.update_layout(xaxis_title='국적', yaxis_title='토론참여수')
fig51.update_layout(width=700)
fig51.update_layout(height=250)
cg_graph71 = plot(fig51, output_type='div')
df1 = pd.DataFrame({"결석일수": data['결석일수'], "발표수": data['발표수']})
print(df1)
df8 = pd.crosstab(df1.결석일수, df1.발표수, margins=True)
print(df8)
df8 = df8.drop(['All'])
fig52 = go.Figure(data=[
go.Bar(name='Under-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[0, :17].values),
go.Bar(name='Above-7',
x=[
'Egypt', 'Iran', 'Iraq', 'Jordan', 'KW', 'Lybia', 'Morocco',
'Palestine', 'SaudiArabia', 'Syria', 'Tunis', 'USA',
'lebanon', 'venzuela'
],
y=df8.iloc[1, :17].values),
])
# Change the bar mode
fig52.update_layout(xaxis_title='국적', yaxis_title='발표수')
fig52.update_layout(width=700)
fig52.update_layout(height=250)
cg_graph72 = plot(fig52, output_type='div')
# 33333 3 3 3 3 - - - - - - -2-2-2- 2- 2- 22 2 2 2 222 3D model
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/student.csv',
encoding='euc-kr')
data['결석일수'] = data['결석일수'].map({'Under-7': 0, 'Above-7': 1})
data['성별'] = data['성별'].map({'M': 0, 'F': 1})
data['성적'] = data['성적'].map({'L': 0, 'M': 1, 'H': 2})
fig54 = px.scatter_3d(data[:480],
x='발표수',
y='토론참여수',
z='새공지사항확인수',
color='결석일수',
size_max=5,
symbol='성별')
# tight layout
fig54.update_layout(margin=dict(l=0, r=0, b=0, t=0))
fig54.update_traces(opacity=1,
marker=dict(showscale=True, reversescale=True, cmid=6))
fig54.update_layout(width=800)
fig54.update_layout(height=700)
fig54.update_layout(plot_bgcolor='rgba(255,255,255,0.5)')
cg_graph74 = plot(fig54, output_type='div')
# 랜덤포레스트 사용
# 모델 평가 생성
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/student.csv',
encoding='euc-kr')
df2 = pd.DataFrame({
"결석일수": data['결석일수'],
"발표수": data['발표수'],
"새공지사항확인수": data['새공지사항확인수'],
"토론참여수": data['토론참여수']
})
df2['결석일수'] = data['결석일수'].map({'Under-7': 0, 'Above-7': 1})
x = df2[['발표수', '토론참여수', '새공지사항확인수']].values # 2차원
y = df2[['결석일수']].values # 1차원
# 여기서부터 분류 예측 모델별 생성 후 정확도 분석
# 모델 평가 생성 - > 정확도 분석
# 랜덤포레스트
new_x = [[0, 20, 10]]
model = RandomForestRegressor(n_estimators=1000, criterion='mse').fit(x, y)
modelflatten = model.predict(x)[:10]
a = model.predict(x)
xh = np.where(a.flatten() > 0.5, 1, 0)
# print(xh.shape)
# print(y.shape)
# print('RandomForestRegressor : ' , accuracy_score(y,xh))
# print('RandomForestRegressor 새로운 값으로 예측 : ' ,model.predict(new_x))
# print('===========================================================')
# LinearRegression
model1 = LinearRegression().fit(x, y)
model1flatten = model1.predict(x)[:10]
# print('예측값 ', np.where(model1flatten.flatten() > 0.5 , 1, 0))
# print('실제값 : ', y[:10].ravel())
a = model1.predict(x)
xh = np.where(a.flatten() > 0.5, 1, 0)
resultLinearRegression = accuracy_score(y, xh)
# print('LinearRegression : ' , resultLinearRegression)
# print('LinearRegression 새로운 값으로 예측 : ' ,model.predict(new_x))
# print('===========================================================')
#
# KNeighborsRegressor
model2 = KNeighborsRegressor(n_neighbors=3).fit(x, y)
model2flatten = model2.predict(x)[:10]
# print('예측값 ', np.where(model2flatten.flatten() > 0.5 , 1, 0))
# print('실제값 : ', y[:10].ravel())
a = model2.predict(x)
xh = np.where(a.flatten() > 0.5, 1, 0)
resultKNeighborsRegressor = accuracy_score(y, xh)
# print('KNeighborsRegressor : ' , accuracy_score(y,xh))
# print('KNeighborsRegressor 새로운 값으로 예측 : ' ,model.predict(new_x))
# print('===========================================================')
#
# XGboost 96%의 확률
model3 = XGBRegressor(n_estimators=100).fit(x, y)
model3flatten = model3.predict(x)[:10]
# print('예측값 ', np.where(model3flatten.flatten() > 0.5 , 1, 0))
# print('실제값 : ', y[:10].ravel())
a = model3.predict(x)
xh = np.where(a.flatten() > 0.5, 1, 0)
resultXGboost = accuracy_score(y, xh)
# print('XGboost : ' , accuracy_score(y,xh))
# print('XGboost 새로운 값으로 예측 : ' ,model.predict(new_x))
# print('===========================================================')
# # = = = = == = = = = = = = 모델별 시각화
import plotly.figure_factory as ff
text = [['모델명', '예측값', '실제값', '정확도'],
[
'RandomForestRegressor',
np.where(modelflatten.flatten() > 0.5, 1, 0), y[:10].ravel(),
accuracy_score(y, xh)
],
[
'LinearRegression',
np.where(model1flatten.flatten() > 0.5, 1, 0), y[:10].ravel(),
resultLinearRegression
],
[
'KNeighborsRegressor',
np.where(model2flatten.flatten() > 0.5, 1, 0), y[:10].ravel(),
resultKNeighborsRegressor
],
[
'XGboost',
np.where(model3flatten.flatten() > 0.5, 1, 0), y[:10].ravel(),
resultXGboost
]]
colorscale = [[0, '#272D31'], [.5, '#ffffff'], [1, '#ffffff']]
font = ['#FCFCFC', 'red', 'black', 'black', 'red']
fig51 = ff.create_table(text, colorscale=colorscale, font_colors=font)
fig51.layout.width = 1300
cg_chart = plot(fig51, output_type='div')
# =================================
#경석씨
df = data
# print(data.columns)
# LabelEncoder
le = LabelEncoder()
# apply "le.fit_transform"
df = df.apply(le.fit_transform)
# 성적 순으로 숫자를 재배치
df.loc[df['성적'] == 0, '성적'] = 3
df.loc[df['성적'] == 2, '성적'] = 2
df.loc[df['성적'] == 1, '성적'] = 1
# print(df['성적'].head())
# # print(df)
# print(df['발표수'].head(20))
# print(np.corrcoef(df['발표수'], df['국적']))
# print(df.corr())
# 피어슨의 상관계수는 일반적으로,
# 값이 -1.0 ~ -0.7 이면, 강한 음적 상관관계
# 값이 -0.7 ~ -0.3 이면, 뚜렷한 음적 상관관계
# 값이 -0.3 ~ -0.1 이면, 약한 음적 상관관계
# 값이 -0.1 ~ +0.1 이면, 없다고 할 수 있는 상관관계
# 값이 +0.1 ~ +0.3 이면, 약한 양적 상관관계
# 값이 +0.3 ~ +0.7 이면, 뚜렷한 양적 상관관계
# 값이 +0.7 ~ +1.0 이면, 강한 양적 상관관계로 해석됩니다.
fig20 = px.imshow(df.corr(),
x=[
'성별', '국적', '출생지', '교육단계', '학년', '학급', '전공', '학기',
'담당부모', '발표수', '과정반복수', '새공지사항확인수', '토론참여수',
'부모의학교만족도', '결석일수', '성적'
],
y=[
'성별', '국적', '출생지', '교육단계', '학년', '학급', '전공', '학기',
'담당부모', '발표수', '과정반복수', '새공지사항확인수', '토론참여수',
'부모의학교만족도', '결석일수', '성적'
],
width=1000,
height=900,
color_continuous_scale='RdBu_r')
fig20.update_layout(width=800,
height=800,
paper_bgcolor='rgba(255,255,255,0)',
plot_bgcolor='rgba(0,0,0,0)',
font=dict(family='Courier New, monospace',
color='#fff',
size=18))
plot20_div = plot(fig20, output_type='div')
# print(studentData[studentData['성적']=='M'].groupby(['전공']).size())
#--------------------------------------
#박윤호
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/education.csv',
encoding='euc-kr')
# print(data)
label = LabelEncoder()
Cat_Colums = data.dtypes.pipe(
lambda Features: Features[Features == 'object']).index
for col in Cat_Colums:
data[col] = label.fit_transform(data[col])
x = data.drop('성적', axis=1)
y = data['성적']
X_train, X_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=52)
model = XGBClassifier(max_depth=10,
learning_rate=0.1,
n_estimators=100,
seed=10)
fit_model = model.fit(X_train, y_train)
pred = fit_model.predict(X_train)
# model.save('yh_xgboost.hdf5')
# model = tf.keras.models.load_model('yh_xgboost.hdf5')
#yh_acc = accuracy_score(y_train, y_test)
#print('예측값 : ', pred[:5])
#print('실제값 : ', np.array(test_y[:5]))
#print('분류 정확도 : ', accuracy_score(test_y, pred))
feature_important = model.get_booster().get_score(importance_type='weight')
keys = list(feature_important.keys())
values = list(feature_important.values())
#print('특성 중요도 :\n{}'.format(model.feature_importances_))
yh_fig1 = go.Figure(
go.Bar(
x=values,
y=keys,
marker=dict(color='#F88137'),
name='성적과 관련된 중요도 그래프',
orientation='h',
))
yh_fig1.update_layout(legend=dict(x=0.029, y=1.038, font_size=10),
margin=dict(l=100, r=20, t=70, b=70),
paper_bgcolor='rgba(255,255,255,0.2)',
plot_bgcolor='rgba(255,255,255,0.2)',
font=dict(color='#000', size=30),
height=600)
yh_fig1.update_layout(yaxis={'categoryorder': 'total ascending'})
yh_grap1 = plot(yh_fig1, output_type='div')
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/education.csv',
encoding='euc-kr')
yh_fig2 = px.scatter(data,
x="발표수",
y="토론참여수",
color="성적",
size='과정반복수',
hover_data=['토론참여수'])
yh_fig2.update_layout(
paper_bgcolor='rgba(255,255,255,0.2)',
plot_bgcolor='rgba(255,255,255,0.2)',
font=dict(color='#000', size=30),
height=550,
width=1400,
)
yh_grap2 = plot(yh_fig2, output_type='div')
data = pd.read_csv(
'https://raw.githubusercontent.com/pyh3887/Django_final_project/master/student.csv',
encoding='euc-kr')
data['성적'] = data['성적'].map({'H': 2, 'M': 1, 'L': 0})
fig = px.scatter_3d(data,
x='발표수',
y='토론참여수',
z='과정반복수',
color='성적',
opacity=0.7)
# tight layout
fig.update_layout(margin=dict(l=0, r=0, b=0, t=0), width=600, height=700)
yh_3D = plot(fig, output_type='div')
#--------------------------------------------------------------
#----------------------------------------------------------------------------
#경석이형
return render(
request, 'full.html', {
'yh_grap1': yh_grap1,
'yh_grap2': yh_grap2,
'yh_3D': yh_3D,
'cg_graph74': cg_graph74,
'cg_graph72': cg_graph72,
'cg_graph71': cg_graph71,
'cg_graph7': cg_graph7,
'yj_grap1': plot_div,
'yj_pie': pie_div,
'yj_grap2': last_div,
'yj_grap3': ab_plot,
'yj_scatter': plot5_div,
'cg_graph1': plot10_div,
'cg_graph2': plot11_div,
'cg_graph3': cg_graph,
'cg_chart': cg_chart,
'heatmap': plot20_div
})