fig = ff.create_distplot(hist_data, group_labels)
st.plotly_chart(fig)
if plot_type2 == "Histogram of Area":
fig = pd.DataFrame(df["area"]).iplot(kind="histogram",
bins=40,
theme="white",
title="Histogram of area",
xTitle='area',
yTitle='Count',
asFigure=True)
st.plotly_chart(fig)
if plot_type2 == "Violin Plot of Area":
fig = px.violin(df, y="area", box=True, points='all')
st.plotly_chart(fig)
if red == "About the Project":
# st.text("hello world")
components.html("""
<div style="background-color:#ff0055;padding:10px">
<h1 style="color:white;text-align:center;">About the Project</h1>
</div>
""")
img_top = """<center><img src="https://i.imgur.com/yOS7IGv.png" width="700px"></center>"""
st.markdown(img_top, unsafe_allow_html=True)
topic = """
data.append(trace)
fig = go.Figure(data=data, layout=layout)
fig.show()
# -
# ### Violin Plot
# +
import plotly.express as px
fig = px.violin(
df_features_targets,
y="g_o",
x="effective_ox_state",
box=True,
points="all",
)
# +
layout = go.Layout(
xaxis=go.layout.XAxis(title=dict(text="Ir Effective Oxidation State", ), ),
yaxis=go.layout.YAxis(title=dict(text="ΔG<sub>O</sub>", ), ),
)
tmp = fig.update_layout(layout)
tmp = fig.update_layout(layout_shared)
# -
print(df[:10][[
'Year', 'Period', 'State', 'Affected by', 'Percent of Colonies Impacted'
]])
#--------------------------------------------------------------------------------
# Build the violin/box plot
violinfig = px.violin(
data_frame=df.query("State == ['{}','{}']".format('TEXAS', 'IDAHO')),
x="Affected by",
y="Percent of Colonies Impacted",
orientation="v",
points='all',
box=True,
color='State',
color_discrete_map={
"TEXAS": "limegreen",
"IDAHO": "red"
},
hover_data=['Period'],
labels={"State": "STATE"},
title='What is killing our Bees',
width=1400,
height=600,
template='plotly_dark',
)
violinfig.update_traces(meanline_visible=True, meanline_color='blue')
pio.show(violinfig)
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
})
import plotly.express as px
df = px.data.tips()
fig = px.strip(df, x="total_bill", y="time", orientation="h", color="smoker")
fig.show()
fig = px.box(df, x="day", y="total_bill", color="smoker", notched=True)
fig.show()
fig = px.violin(df,
y="tip",
x="smoker",
color="sex",
box=True,
points="all",
hover_data=df.columns)
fig.show()
def make_grouped_plot(
self,
ensembles: list,
parameters: List[Any],
plot_type: str = "distribution",
) -> go.Figure:
"""Create subplots for selected parameters"""
df = self.dataframe_melted.copy()
df = df[df["ENSEMBLE"].isin(ensembles)]
df = df[df["PARAMETER"].isin(parameters)]
df = self._sort_parameters_col(df, parameters)
if plot_type == "distribution":
fig = (px.violin(
df,
x="VALUE",
facet_col="PARAMETER",
facet_col_wrap=min(
min([
x for x in range(100)
if (x * (x + 1)) >= len(parameters)
]),
20,
),
facet_row_spacing=max((0.08 - (0.00071 * len(parameters))),
0.03),
color="ENSEMBLE",
color_discrete_sequence=self.colorway,
custom_data=["PARAMETER"],
).update_xaxes(
matches=None,
fixedrange=True,
title=None,
showticklabels=len(parameters) <= 100,
tickangle=0,
tickfont_size=max((18 - (0.4 * len(parameters))), 10),
).update_yaxes(
showticklabels=False).for_each_trace(lambda t: t.update(
y0=0,
hoveron="violins",
hoverinfo="none",
meanline_visible=True,
orientation="h",
side="positive",
width=2,
points=False,
)).for_each_annotation(lambda a: a.update(
text=(a.text.split("=")[-1]),
visible=len(parameters) <= 42,
font_size=max((18 - (0.4 * len(parameters))), 10),
)))
# Create invisible boxes used for hoverinfo on the violin plots
# Necessary due to https://github.com/plotly/plotly.js/issues/2145
ensembles = df["ENSEMBLE"].unique()
hovertraces = []
for trace in fig["data"]:
parameter = trace["customdata"][0][0]
# check of parameter value to determine print formatter
value = abs(
self.get_stat_value(parameter, ensembles[0],
stat_column="Avg"))
form = ".1f" if value > 10 else ".2g"
hovertraces.append(
go.Scatter(
x=[min(trace.x),
min(trace.x),
max(trace.x),
max(trace.x)],
y=[0, 1, 1, 0],
xaxis=trace.xaxis,
yaxis=trace.yaxis,
mode="lines",
fill="toself",
opacity=0,
showlegend=False,
text=(f"<b>{parameter}</b><br>" + "<br>".join(
f"<b>{ens}:</b><br>"
"Avg: "
f"{self.get_stat_value(parameter, ens, stat_column='Avg'):{form}}<br>"
"Std: "
f"{self.get_stat_value(parameter, ens, stat_column='Stddev'):{form}}"
for ens in ensembles)),
hoverinfo="text",
hoverlabel=dict(bgcolor="#E6FAEC",
font=dict(color="#243746", size=15)),
))
fig = fig.to_dict()
fig["data"].extend(hovertraces)
fig["layout"] = self.theme.create_themed_layout(fig["layout"])
fig["layout"].update(paper_bgcolor="white", plot_bgcolor="white")
return fig
import json
import pandas as pd
import plotly
import plotly.express as px
file = 'задание 14.xls'
xl = pd.read_excel(file)
fig4 = px.violin(xl,
x='предмет',
y='балл',
color="округ",
template='presentation',
points='outliers',
box=True)
fig4.show()
fig4.write_html('file.html')
print(plotly.io.to_json(fig4))
with open('file.json', 'w', encoding='utf-8') as f:
json.dump(fig4,
f,
cls=plotly.utils.PlotlyJSONEncoder,
ensure_ascii=False,
indent=4)
def generate_report(self):
grouped = self.all_rejects[[
'journal', 'count'
]].groupby("journal").count() # journal becomes the index
if not self.selected_external_journal_names:
external_jou_names = grouped.sort_values(by='count',
ascending=False)
self.selected_external_journal_names = list(
external_jou_names[:self.n_top].index)
external_journals = self.found[self.found['journal'].isin(
self.selected_external_journal_names)].copy()
my_journal = self.found[self.found['decision'] == 'accepted'].copy()
virtual_journal = pd.concat([external_journals, my_journal])
external_journals['category'] = 'Assemblage'
virtual_journal['category'] = 'Cuvee'
my_journal['category'] = 'Grand Cru'
fig = px.violin(
pd.concat([external_journals, virtual_journal, my_journal]),
y="citations",
x="category",
category_orders={"category": ['Grand Cru', 'Cuvee', 'Assemblage']},
# color_discrete_sequence=px.colors.qualitative.G10,
color_discrete_map={
"Grand Cru": "lime",
"Cuvee": "red",
'Assemblage': "orange"
},
points="all",
title=f"Citation distributions",
color="category",
template="plotly_dark",
hover_name="journal",
hover_data={
"citations": False,
"decision": False,
"category": False,
"doi": True,
"retrieved_title": True,
"original_title": True,
"manuscript_nm": True,
})
fig.update_traces(
marker={
"opacity": 0.4,
"size": 5,
"symbol":
'circle-open' # https://plotly.com/python/marker-style/#custom-marker-symbols
},
jitter=0.6,
meanline_visible=True,
)
fig.update_layout(height=800)
fig.update_xaxes(tickfont_size=24)
fig.update_yaxes(tickfont_size=24)
# fig.add_annotation(
# x=1.1, y=0.95, xref="paper", yref="paper",
# text=f"Average number<br>of transfers:<br>{avg_transfer:.2f}",
# showarrow=False,
# font={"size": 12}
# )
return fig
fig.write_html(os.path.join(dir_name, "histogram_histfunc.html"))
tips = px.data.tips()
fig = px.strip(tips, x="total_bill", y="time", orientation="h", color="smoker")
fig.write_html(os.path.join(dir_name, "strip.html"))
tips = px.data.tips()
fig = px.box(tips, x="day", y="total_bill", color="smoker", notched=True)
fig.write_html(os.path.join(dir_name, "box.html"))
tips = px.data.tips()
fig = px.violin(
tips,
y="tip",
x="smoker",
color="sex",
box=True,
points="all",
hover_data=tips.columns,
)
fig.write_html(os.path.join(dir_name, "violin.html"))
# #### Ternary Coordinates
election = px.data.election()
fig = px.scatter_ternary(
election,
a="Joly",
b="Coderre",
c="Bergeron",
color="winner",
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
df = pd.read_csv('airbnb_NYC_2019.csv')
fig = px.scatter_mapbox(df,
lat="latitude",
lon="longitude",
color="neighbourhood_group",
zoom=9)
fig.update_layout(mapbox_style="carto-positron")
figSunburst = px.sunburst(df,
path=['neighbourhood_group', 'room_type'],
values='price')
room_histogram = px.histogram(df, x="room_type", color="neighbourhood_group")
violin_fig = px.violin(df, y="price", x='neighbourhood_group', box=True)
treemap_fig = px.treemap(
df,
path=[px.Constant('nyc'), 'neighbourhood_group', 'neighbourhood'],
values='price',
hover_data=['neighbourhood'])
app.layout = html.Div([
html.H1(children='Airbnb NYC',
style={
'font-family': 'Helvetica',
'textAlign': 'center'
}),
html.Div([
html.Label('Select a neighborhood', style={'font-family':
'Helvetica'}),
def main():
st.title("Speech Emotion Recognition")
st.sidebar.markdown("### Use the menu to navigate on the site")
img = Image.open("images/emotion3.jpg")
with st.sidebar:
st.image(img, width=300)
menu = ["Emotion recognition", "Dataset description", "Our team", "Leave feedback"]
choice = st.sidebar.selectbox("Menu", menu)
if choice == "Emotion recognition":
audio_file = st.file_uploader("Upload audio file", type=['wav'])
if st.button('Record'):
with st.sidebar.spinner(f'Recording for 5 seconds ....'):
st.sidebar.write("Recording...")
time.sleep(3)
st.sidebar.success("Recording completed")
if audio_file is not None:
st.markdown("## Analyzing...")
st.sidebar.subheader("Audio file")
file_details = {"Filename": audio_file.name, "FileSize": audio_file.size}
st.sidebar.write(file_details)
st.audio(audio_file, format='audio/wav', start_time=0)
st.sidebar.markdown("### Settings:")
show_more_labels = st.sidebar.checkbox("Show prediction for 7 emotions")
show_mel = st.sidebar.checkbox("Show Mel-spec model prediction")
show_gender = st.sidebar.checkbox("Show gender prediction")
path = os.path.join("audio", audio_file.name)
save_audio(audio_file)
# extract features
wav, sr = librosa.load(path, sr=44100)
Xdb = get_melspec(path)[1]
fig, ax = plt.subplots(1, 2, figsize=(12, 4), sharex=True)
fig.set_facecolor('#d1d1e0')
plt.subplot(211)
plt.title("Wave-form")
librosa.display.waveplot(wav, sr=sr)
plt.gca().axes.get_yaxis().set_visible(False)
plt.gca().axes.get_xaxis().set_visible(False)
plt.gca().axes.spines["right"].set_visible(False)
plt.gca().axes.spines["left"].set_visible(False)
plt.gca().axes.spines["top"].set_visible(False)
plt.gca().axes.spines["bottom"].set_visible(False)
plt.gca().axes.set_facecolor('#d1d1e0')
plt.subplot(212)
plt.title("Mel-log-spectrogram")
librosa.display.specshow(Xdb, sr=sr, x_axis='time', y_axis='hz')
plt.gca().axes.get_yaxis().set_visible(False)
plt.gca().axes.spines["right"].set_visible(False)
plt.gca().axes.spines["left"].set_visible(False)
plt.gca().axes.spines["top"].set_visible(False)
st.write(fig)
st.markdown("## Getting the result...")
# mfccs model results
with st.spinner('Wait for it...'):
mfccs = get_mfccs(path, model.input_shape[-1])
mfccs = mfccs.reshape(1, *mfccs.shape)
pred = model.predict(mfccs)[0]
txt = "MFCCs\n" + get_title(pred)
fig = plt.figure(figsize=(10, 4))
plot_emotions(data6=pred, fig=fig, title=txt)
st.write(fig)
if show_more_labels:
with st.spinner('Wait for it...'):
model_ = load_model("model4.h5")
mfccs_ = get_mfccs(path, model_.input_shape[-2])
mfccs_ = mfccs_.T.reshape(1, *mfccs_.T.shape)
pred = model_.predict(mfccs_)[0]
txt = "MFCCs\n" + get_title(pred, CAT7)
fig = plt.figure(figsize=(10, 4))
plot_polar(fig, predictions=pred, categories=CAT7, title=txt)
st.write(fig)
if show_gender:
with st.spinner('Wait for it...'):
gmodel = load_model("model_mw.h5")
gmfccs = get_mfccs(path, gmodel.input_shape[-1])
gmfccs = gmfccs.reshape(1, *gmfccs.shape)
gpred = gmodel.predict(gmfccs)[0]
gdict = [["female","woman.png"], ["male","man.png"]]
ind = gpred.argmax()
txt = "Predicted gender: " + gdict[ind][0]
st.subheader(txt)
img = Image.open("images/"+ gdict[ind][1])
st.image(img, width=300)
if show_mel:
#################################################################################
st.subheader("This section was disabled")
st.write("Since we are currently using a free tier instance of AWS, "
"we are not going to deploy this model.\n\n"
"If you want to try it we recommend to clone our GitHub repo")
link = '[GitHub](https://github.com/CyberMaryVer/speech-emotion-webapp)'
st.markdown(link, unsafe_allow_html=True)
st.write("After that, just uncomment this section in the main file "
"to use the mel-spectrograms model:")
code = '''
# tmodel = load_model("tmodel_all.h5")
#
# # mel-spec model results
# mel = get_melspec(path)[0]
# mel = mel.reshape(1, *mel.shape)
# tpred = tmodel.predict(mel)[0]
# txt = "Mel-spectrograms" + get_title(tpred)
# fig = plt.figure(figsize=(10, 4))
# plot_emotions(data6=tpred, fig=fig, title=txt)
# st.write(fig)'''
st.code(code, language='python')
#################################################################################
############## Uncomment this section below to enable the model #################
# tmodel = load_model("tmodel_all.h5")
#
# # mel-spec model results
# mel = get_melspec(path)[0]
# mel = mel.reshape(1, *mel.shape)
# tpred = tmodel.predict(mel)[0]
# txt = "Mel-spectrograms\n" + get_title(tpred)
# fig = plt.figure(figsize=(10, 4))
# plot_emotions(data6=tpred, fig=fig, title=txt)
# st.write(fig)
#################################################################################
elif choice == "Dataset description":
st.subheader("Dataset analysis")
link = '[GitHub](https://github.com/talbaram3192/Emotion_Recognition)'
st.markdown(link, unsafe_allow_html=True)
df = pd.read_csv("df_audio.csv")
fig = px.violin(df, y="source", x="emotion4", color="actors", box=True, points="all", hover_data=df.columns)
st.plotly_chart(fig, use_container_width=True)
# st.write(df.source.value_counts())
# st.write(df.actors.value_counts())
# st.write(df.emotion4.value_counts())
elif choice == "Our team":
st.subheader("Our team")
st.info("*****@*****.**")
st.info("*****@*****.**")
st.info("*****@*****.**")
st.balloons()
else:
st.subheader("Leave feedback")
user_input = st.text_area("Your feedback is greatly appreciated")
user_name = st.selectbox("Choose your personality", ["checker1","checker2","checker3","checker4"])
if st.button("Submit"):
log_file(user_name + " " + user_input)
st.success(f"Message\n\"\"\"{user_input}\"\"\"\nwas sent")
thankimg = Image.open("images/sticky.png")
st.image(thankimg)
def main():
start_t = datetime.now()
# Input dataset
dataset = datasets.load_diabetes()
X = dataset.data
y = dataset.target
for idx, column in enumerate(X.T):
feature_name = dataset.feature_names[idx]
predictor = statsmodels.api.add_constant(column)
# Continuous predictor, X, and continuous response, y
if y.dtype == np.number and X.dtype == np.number:
linear_regression_model = statsmodels.api.OLS(y, predictor)
linear_regression_model_fitted = linear_regression_model.fit()
print(f"Variable: {feature_name}")
print(linear_regression_model_fitted.summary())
# Get the stats
t_value = round(linear_regression_model_fitted.tvalues[1], 6)
p_value = "{:.6e}".format(
linear_regression_model_fitted.pvalues[1])
# Plot the figure to a local html file
fig = px.scatter(x=column, y=y, trendline="ols")
fig2 = px.histogram(x=column, nbins=20)
# This is not working, giving NaN
_, bins = np.histogram(column, bins=20)
bin_means = pd.Series(column).groupby(pd.cut(column, bins)).mean()
Sumallll = sum(column)
pop_avg = Sumallll / all(column)
Diff = 1 / 20 * sum(bin_means - pop_avg)**2
fig.update_layout(
title=
f"Variable:{feature_name}:(t-value={t_value})(p-value={p_value})",
xaxis_title=f"Variable: {feature_name}",
yaxis_title="y",
)
fig2.update_layout(
title=f"Variable:{feature_name}:Mean difference = {Diff}",
xaxis_title=f"Variable: {feature_name}",
yaxis_title="count",
)
with open("./p_graph.html", "a") as f:
f.write(fig.to_html(full_html=False, include_plotlyjs="cdn"))
f.write(fig2.to_html(full_html=False, include_plotlyjs="cdn"))
# Categorical predictor, X, and continuous response, y
elif y.dtype == np.number and X.dtype != np.number:
logistic_regression_model = LogisticRegression(
random_state=1234).fit(predictor, y)
print(f"Variable: {feature_name} Fit Score")
print(logistic_regression_model.score(predictor, y))
score = logistic_regression_model.score(predictor, y)
# Plot the Figure to a local html file
fig = px.violin(x=y, y=column)
fig.update_layout(
title=
f"Variable:{feature_name},Logistic Regression Fit Score={score}",
xaxis_title=f"Variable: {feature_name}",
yaxis_title="y",
)
with open("./p_graph.html", "a") as f:
f.write(fig.to_html(full_html=False, include_plotlyjs="cdn"))
# Continuous predictor, X, and categorical response, y
elif y.dtype != np.number and X.dtype == np.number:
logistic_regression_model = LogisticRegression(
random_state=1234).fit(predictor, y)
print(f"Variable: {feature_name} Fit Score")
print(logistic_regression_model.score(predictor, y))
score = logistic_regression_model.score(predictor, y)
# Plot the Figure to a local html file
fig = px.violin(x=y, y=column)
fig.update_layout(
title=
f"Variable: {feature_name},Logistic Regression Fit Score={score}",
xaxis_title=f"Variable: {feature_name}",
yaxis_title="y",
)
with open("./p_graph.html", "a") as f:
f.write(fig.to_html(full_html=False, include_plotlyjs="cdn"))
else:
# Categorical response, X, categorical response, y
logistic_regression_model = LogisticRegression(
random_state=1234).fit(predictor, y)
print(f"Variable: {feature_name} Fit Score")
print(logistic_regression_model.score(predictor, y))
score = logistic_regression_model.score(predictor, y)
# Plot the Figure to a local html file
fig = px.violin(x=y, y=column)
fig.update_layout(
title=
f"Variable:{feature_name},Logistic Regression Fit Score={score}",
xaxis_title=f"Variable: {feature_name}",
yaxis_title="y",
)
with open("./p_graph.html", "a") as f:
f.write(fig.to_html(full_html=False, include_plotlyjs="cdn"))
# Continuous predictor, X, and continuous response, y
if y.dtype == np.number and X.dtype == np.number:
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
regressor = RandomForestRegressor(n_estimators=200, random_state=0)
regressor.fit(X_train, y_train)
y_pred = regressor.predict(X_test)
print("******Random forest regression performance*******")
print("Mean Absolute Error:",
metrics.mean_absolute_error(y_test, y_pred))
print("Mean Squared Error:",
metrics.mean_squared_error(y_test, y_pred))
print(
"Root Mean Squared Error:",
np.sqrt(metrics.mean_squared_error(y_test, y_pred)),
)
importances = regressor.feature_importances_
indices = np.argsort(importances)[::-1]
print("*****Feature ranking:*****")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" %
(f + 1, indices[f], importances[indices[f]]))
# Categorical predictor, X, and continuous response, y
elif y.dtype == np.number and X.dtype != np.number:
rf = RandomForestClassifier(max_depth=2, random_state=0)
rf.fit(X, y)
importances = rf.feature_importances_
indices = np.argsort(importances)[::-1]
print("*****Feature ranking:*****")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" %
(f + 1, indices[f], importances[indices[f]]))
# Continuous predictor, X, and categorical response, y
elif y.dtype != np.number and X.dtype == np.number:
rf = RandomForestClassifier(max_depth=2, random_state=0)
rf.fit(X, y)
importances = rf.feature_importances_
indices = np.argsort(importances)[::-1]
print("*****Feature ranking:*****")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" %
(f + 1, indices[f], importances[indices[f]]))
else:
# Categorical response, X, categorical response, y
rf = RandomForestClassifier(max_depth=2, random_state=0)
rf.fit(X, y)
importances = rf.feature_importances_
indices = np.argsort(importances)[::-1]
print("*****Feature ranking:*****")
for f in range(X.shape[1]):
print("%d. feature %d (%f)" %
(f + 1, indices[f], importances[indices[f]]))
print(f" {(datetime.now() - start_t)} seconds")
def plot_age(self):
top_k_countries = self.countries_to_plot["Country"][:5]
df_top_countries = self.df.loc[self.df['Country'].isin(top_k_countries)].copy()
df_top_countries_by_age = df_top_countries.sort_values(by="Age", ascending=True)
return px.violin(df_top_countries_by_age, y="Age", x="Country", title="Relationship between countries and age",
hover_data=self.df.columns)
# ### Plotting
# #### (1) To get the Service with the most content.
# In[9]:
tv_shows_combined.groupby('StreamingOn').Title.count().plot(kind='bar')
# #### (2) Violin charts to gauge the content rating(IMDB) and freshness (Rotten Tomatoes) accross all the streaming service.
# In[10]:
figure = []
figure.append(
px.violin(tv_shows_both_ratings,
x='StreamingOn',
y='IMDb',
color='StreamingOn'))
figure.append(
px.violin(tv_shows_both_ratings,
x='StreamingOn',
y='Rotten Tomatoes',
color='StreamingOn'))
fig = make_subplots(rows=2, cols=4, shared_yaxes=True)
for i in range(2):
for j in range(4):
fig.add_trace(figure[i]['data'][j], row=i + 1, col=j + 1)
fig.update_layout(autosize=False, width=800, height=800)
fig.show()
# Correlation matrix
st.subheader("Feature correlation")
st.write("Correlation matrix that shows the features that have highest \
linear correlation with metallicity. Each quantity is calculated purely \
based on the crystal composition.")
corr = data.corr().abs()
top_5 = corr["is_metal"].sort_values(ascending=False).index[:5]
corr = data[top_5].corr().abs()
corr_fig = px.imshow(corr)
st.plotly_chart(corr_fig)
# Feature relationships
top_3 = corr["is_metal"].sort_values(ascending=False).index[1:4]
for idx, col in enumerate(top_3):
box_fig = px.violin(data,
x="Metal vs Nonmetal",
y=col,
box=True,
color="Metal vs Nonmetal")
st.plotly_chart(box_fig)
# Pivot tables
st.subheader("Pivot tables")
st.write("Pivot tables help us understand the statistical relationships "
"between a target variable and other descriptors of a sample.")
table = pd.pivot_table(data,
index="Metal vs Nonmetal",
values=top_3,
aggfunc=[np.mean, np.median, np.var])
st.write(table)
df = pd.melt(sales, id_vars=['id', 'item_id', 'dept_id', 'cat_id', 'store_id', 'state_id'], var_name='d', value_name='sold').dropna() ## Merge calendar and prices dataframes into df df = pd.merge(df, calendar, on='d', how='left') df = pd.merge(df, prices, on=['store_id','item_id','wm_yr_wk'], how='left') ## EXPLORATORY DATA ANALYSIS ## ## Check average sale price for each item ## the groupby function, groups together specific columns and column values. Here I specify that I want the ## average sell price to be from each state, store and item group_price_store = df.groupby(['state_id','store_id','item_id'],as_index=False)['sell_price'].mean().dropna() ## Using plotly express, plot the prices vs the store. Display different colours for the state and use the hover ## property to identify which item is present fig = px.violin(group_price_store, x='store_id', color='state_id', y='sell_price',box=True, hover_name='item_id') fig.update_xaxes(title_text='Store') fig.update_yaxes(title_text='Selling Price($)') fig.update_layout(template='seaborn',title='Distribution of Items prices wrt Stores',legend_title_text='State') fig.show() ## FEATURE ENGINEERING ## ## Label encoding ## Store the different categories found in each column with their corresponding codes d_id = dict(zip(df.id.cat.codes, df.id)) d_item_id = dict(zip(df.item_id.cat.codes, df.item_id)) d_dept_id = dict(zip(df.dept_id.cat.codes, df.dept_id)) d_cat_id = dict(zip(df.cat_id.cat.codes, df.cat_id)) d_store_id = dict(zip(df.store_id.cat.codes, df.store_id)) d_state_id = dict(zip(df.state_id.cat.codes, df.state_id))
def test_update_graph(df_2019, var_to_filter, filter, var_to_see, score_to_see):
df = filter_function(df_2019, var_to_filter, filter)
df.sort_values(var_to_see, inplace=True)
return px.violin(df, x=var_to_see, y=score_to_see, box=True)
def violinPlot(self, df, yName, title=None):
"""Create and show a violin plot"""
# create violin plot
fig = px.violin(df, y=yName)
fig.show()
email.drop(['Unnamed: 0', 'filename', 'Message-ID'],axis=1,inplace=True)
email.groupby('Class').describe().T
email['label'] = email['Class'].map({'Non Abusive': 0, 'Abusive': 1}) # add 'label' column
sns.set_style('whitegrid')
sns.countplot(email['Class'])
plt.title('Distribution of Abusive and Non_Abusive')
# Make a new column to show the length of content messages
email['length'] = email['content'].apply(len)
import plotly.express as px
fig = px.violin(data_frame=email, y="length", points="all", color="Class",
width=800, height=600)
fig.show()
# it shows median length of Abusive mail = 591.5 & Non_aAbusive = 735
colors = ['#ff9999','#66b3ff']
email["Class"].value_counts().plot(kind = 'pie',colors = colors ,explode = (0.1,0),autopct = '%1.1f%%')
from collections import Counter
count1 = Counter(" ".join(email[email['Class']=='Non Abusive']["content"]).split()).most_common(30)
df1 = pd.DataFrame.from_dict(count1)
df1 = df1.rename(columns={0: "words in Non-Abusive", 1 : "count"})
count2 = Counter(" ".join(email[email['Class']=='Abusive']["content"]).split()).most_common(30)
df2 = pd.DataFrame.from_dict(count2)
df2 = df2.rename(columns={0: "words in Abusive", 1 : "count_"})
def main():
st.sidebar.title('O que você gostaria de ver?')
opcao = ['Análise Estatística', 'Gráficos', 'Referências']
choice = st.sidebar.radio(' ', opcao)
st.sidebar.title('Data')
st.sidebar.info("""
Caso não tenha um arquivo csv por perto, você pode baixar por aqui:\n
[Titanic](http://kopasite.net/up/1/titanic.csv)\n
[Iris](http://kopasite.net/up/0/iris.csv)\n
[Tips](http://kopasite.net/up/0/tips.csv)\n
""")
st.sidebar.title('Créditos')
st.sidebar.info("""
Feito por Raul.\n
[github](https://github.com/taikutsu91)
[linkedin](https://www.linkedin.com/in/raul-avelino-959b16149)\n
Duvidas ou informações:
[email protected] ou
[email protected]\n
Para mais informações do projeto ver Referências.
""")
if choice == 'Análise Estatística':
st.header('Análise Estatística')
st.subheader("""
Para começar carregue um arquivo csv.
""")
data = st.file_uploader(' ', type=['csv'])
if data is not None:
df = pd.read_csv(data)
st.write(df.head())
aux = pd.DataFrame({'colunas': df.columns, 'tipos': df.dtypes})
col_num = list(aux[aux['tipos'] != 'object']['colunas'])
col_obj = list(aux[aux['tipos'] == 'object']['colunas'])
colunas = list(df.columns)
hue = df.columns[df.nunique() < 10].values.tolist()
if st.checkbox('Tamanho DataFrame'):
st.write('Número de linhas', df.shape[0])
st.write('Número de colunas', df.shape[1])
if st.checkbox('Mostrar colunas'):
colunas = list(df.columns)
st.write(colunas)
if st.checkbox('Mostrar tipos das colunas'):
st.write(df.dtypes)
if st.checkbox('Mostrar Sumário'):
st.write(df.describe())
if st.checkbox('Mostrar % valores nulos'):
st.write(df.isnull().mean() * 100)
if st.checkbox('Escolha uma coluna númerica'):
coluna_num = st.selectbox('Coluna', col_num)
st.write('Média', df[coluna_num].mean())
st.write('Moda', df[coluna_num].mode()[0])
st.write('Desvio Padrão', df[coluna_num].std())
st.write('Maior Valor', df[coluna_num].max())
st.write('Menor Valor', df[coluna_num].min())
st.write('% datos faltantes',
(df[coluna_num].isnull().mean() * 100))
st.write('Valores únicos na coluna', df[coluna_num].nunique())
elif choice == 'Gráficos':
st.header('Visualização dos Dados.')
st.subheader('Para começar carregue um arquivo csv.')
st.info(""" Alguns gráficos terão uma opção para selecionar a cor.
A opção cor vai determinar qual coluna no dataframe deve ser usada para codificação de cores,
adicionando o parâmetro cor, indica para o gráfico que você deseja colorir os dados de maneira diferente com base na coluna selecionada.
""")
data = st.file_uploader(' ', type=['csv'], key='graficos')
if data is not None:
df = pd.read_csv(data)
st.write(df.head())
aux = pd.DataFrame({'colunas': df.columns, 'tipos': df.dtypes})
col_num = list(aux[aux['tipos'] != 'object']['colunas'])
col_obj = list(aux[aux['tipos'] == 'object']['colunas'])
colunas = list(df.columns)
hue = df.columns[df.nunique() < 10].values.tolist()
st.info("""
Caso seu dataframe seja muito grande, você pode selecionar um sample do mesmo,
escolhendo qual a porcentagem dos dados que serão usadas.
""")
pct = st.slider("Sample size % :", int(0), int(100), int(100))
frame = df.sample(frac=(pct / 100))
if st.checkbox('Tamanho do DataFrame'):
st.write('Número de linhas', frame.shape[0])
st.write('Número de colunas', frame.shape[1])
if st.checkbox('Scatter Plot'):
eixo_x = st.selectbox('Selecione Eixo X',
col_num,
key='unique')
eixo_y = st.selectbox('Selecione Eixo Y',
col_num,
key='unique')
cor = st.selectbox('Cor', hue, key='unique')
fig = px.scatter(frame,
x=eixo_x,
y=eixo_y,
color=cor,
template=cmap,
title=f'Scatter Plot {eixo_x} x {eixo_y}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Histogram'):
st.info("""
Caso o parâmetro cor tenha algum dado faltante o mesmo será preenchido,
automaticamente com a moda da coluna selecionada.
""")
coluna_num = st.selectbox('Selecione Eixo X',
col_num,
key='coluna_num')
color = st.selectbox('Cor', hue, key='color')
fig1 = px.histogram(frame,
x=coluna_num,
color=frame[color].fillna(
frame[color].mode()),
histfunc='sum',
title=f'Histogram {coluna_num}')
st.plotly_chart(fig1, use_container_width=True)
if st.checkbox('Counts'):
st.info("""
Este gráfico retorna, os valores únicos do dataframe em porcetagem,
com base na coluna selecionada.
""")
value = st.selectbox('Selecione uma coluna',
colunas,
key='value')
plot_value = frame[value].value_counts(normalize=True)
fig = plot_value.plot(kind='bar',
title=f'Count Coluna: {value}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Bar Plot'):
cols = st.selectbox('Selecione uma coluna',
colunas,
key='cols')
target = st.selectbox('Cor', hue, key='target')
gb = pd.crosstab(frame[cols], frame[target])
fig = gb.plot(kind='bar', title=f'Bar Plot {cols} x {target}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Violin Plot'):
coluna_num1 = st.selectbox('Selecione o Eixo X',
col_obj,
key='coluna_num1')
coluna_x1 = st.selectbox('Selecione o Eixo Y',
col_num,
key='coluna_x1')
color1 = st.selectbox('Cor', hue, key='color1')
fig = px.violin(
frame,
x=coluna_num1,
y=coluna_x1,
color=color1,
title=f'Violet Plot {coluna_num1} x {coluna_x1}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Box Plot'):
coluna_num2 = st.selectbox('Selecione o Eixo X',
col_obj,
key='coluna_num2')
coluna_x2 = st.selectbox('Selecione o Eixo Y',
col_num,
key='coluna_x2')
color2 = st.selectbox('Cor', hue, key='color2')
fig = px.box(frame,
x=coluna_num2,
y=coluna_x2,
color=color2,
title=f'Box Plot {coluna_num2} x {coluna_x2}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Line Plot'):
st.info("""
Line Plot é normalmanete usado para medir variações atráves do tempo,
caso seu dataframe não tenha uma coluna que seja datetime , não é recomendado o uso do Line Plot,
use Scatter Plot ou Bar Plot.
""")
eixo_x2 = st.selectbox('Selecione o Eixo X',
colunas,
key='eixo_x2')
eixo_y2 = st.selectbox('Selecione o Eixo Y',
colunas,
key='eixo_y2')
fig = frame.plot(kind='line',
x=eixo_x2,
y=eixo_y2,
title=f'Line Plot {eixo_x2} x {eixo_y2}')
st.plotly_chart(fig, use_container_width=True)
if st.checkbox('Heatmap'):
metodo = st.selectbox('Selecione o Método de correlação',
['pearson', 'kendall', 'spearman'],
key='metodo')
corr = frame.corr(method=metodo)
ax = sns.heatmap(corr, annot=True, fmt=".2f", cmap="YlGnBu")
st.pyplot()
if st.checkbox('Heatmap Colunas'):
st.info(
"""Você pode selecionar quais colunas você quer usar para fazer seu heatmap.
""")
metodo1 = st.selectbox('Selecione o Método de correlação',
['pearson', 'kendall', 'spearman'],
key='metodo1')
cols = st.multiselect('Selecione colunas que serão usadas',
col_num,
key='cols')
corr = frame[cols].corr(method=metodo1)
ax = sns.heatmap(corr, annot=True, fmt=".2f", cmap="YlGnBu")
st.pyplot()
elif choice == 'Referências':
st.image(codenation, width=800, format='PNG')
st.header('Referências')
st.write("""
Esse projeto foi proposto pelo Professor [Túlio Souza](https://www.linkedin.com/in/tuliovieira/) da [Codenation](https://www.codenation.dev/), na semana 3 do Acelera Dev Data Science turma do meio do ano de 2020.
Para saber mais sobre a codenation e seus "Aceleramentos" de carreira e ver o trabalho incrível que eles fazem, podem entra no [Site Codenation](https://www.codenation.dev/), [facebook](https://pt-br.facebook.com/dev.codenation) ou pelo
[linkedin](https://br.linkedin.com/company/code-nation).
""")
st.subheader('Gráficos')
st.write("""
Alguns gráficos desse projeto foram feitos usando a biblioteca plotly e sua extensão para pandas.
https://plotly.com/python/bar-charts/ \n
https://plotly.com/python/pandas-backend/ \n
Heatmap foi feito usando seaborn.\n
https://seaborn.pydata.org/generated/seaborn.heatmap.html\n
Os datasets no menu lateral foram arquivados no site kopasite.net, uma ótima forma de guardar arquivos curtos e com download simples.\n
http://kopasite.net/upload
Para informações adicionais do streamlit acesse: \n
https://docs.streamlit.io/ \n
https://www.streamlit.io/ \n
Tips e iris data set foram retirados.\n
https://github.com/mwaskom/seaborn-data\n
Titanic data set.\n
https://www.kaggle.com/c/titanic\n
Deploy do projeto feito no heroku:\n
https://www.youtube.com/watch?v=mQ7rGcE766k
Obrigado por ver meu primeiro app e obrigado codenation pela oportunidade de aprender, qualquer dúvida manda um email.\n
[email protected] ou [email protected]
""")
visible_table = cache_get(session_id, CACHE_KEYS['visible_table'])
filtered_table = filter_all(
data,
num_keys,
num_values,
cat_keys,
cat_values,
visible_table,
visible_list
)
if c_violin == 'None':
violin_fig = px.violin(filtered_table,
x=x_key,
y=y_key,
box=True,
violinmode='group',
labels={x_key: x_label,
y_key: y_label})
else:
violin_fig = px.violin(filtered_table,
x=x_key,
y=y_key,
color=c_violin,
box=True,
violinmode='group',
labels={x_key: x_label,
y_key: y_label})
else:
violin_fig = {
'data': [{'type': 'histogram',
value=[], #list(self.volumes["SOURCE"])[0]
placeholder="Select months",
style={'backgroundColor': '#1E1E1E'},
className='monthselector'),
],
style={'color': '#1E1E1E'})
]),
html.Div(className='eight columns div-for-charts',
children=[
dcc.Graph(id='up_down',
config={'displayModeBar': False},
animate=True,
figure=px.violin(
template='plotly_dark').update_layout({
'plot_bgcolor':
'rgba(0, 0, 0, 0)',
'paper_bgcolor':
'rgba(0, 0, 0, 0)'
}))
])
]),
html.Br(),
html.Br(),
html.Br(),
html.Br(),
html.Div(
className='row',
children=[
html.Div(
className='four columns div-user-controls',
children=[
def main():
# reading in the data
column_names = [
"sepal_length",
"sepal_width",
"petal_length",
"petal_width",
"class",
]
iris_df = pd.read_csv(
"C:/Users/KRATI PATIDAR/Desktop/BDA696_MLE/iris.data", names=column_names
)
print(iris_df.head())
# summary statistics
iris_arr = iris_df.to_numpy()
print(iris_arr)
print("Mean = ", np.mean(iris_df))
print("Minimum = ", np.min(iris_df))
print("Maximum = ", np.max(iris_df))
print("First quantile = ", np.quantile(iris_arr[:, :-1], q=0.25, axis=0))
print("Second quantile = ", np.quantile(iris_arr[:, :-1], q=0.50, axis=0))
print("Third quantile = ", np.quantile(iris_arr[:, :-1], q=0.75, axis=0))
print("Fourth quantile = ", np.quantile(iris_arr[:, :-1], q=1, axis=0))
print(iris_df["class"].unique())
# making plots
plot_1 = px.scatter(
iris_df,
x="sepal_width",
y="sepal_length",
size="petal_length",
hover_data=["petal_width"],
color="class",
title="Scatter Plot for all variables for different classes",
)
plot_1.show()
plot_2 = px.line(
iris_df,
x="petal_width",
y="petal_length",
color="class",
title="Line Plot for Petal Width and Petal Length for all classes",
)
plot_2.show()
plot_3 = px.violin(
iris_df,
x="sepal_width",
y="sepal_length",
color="class",
title="Violin Plot for sepal length and sepal width for all classes",
)
plot_3.show()
plot_4 = px.scatter_3d(
iris_df,
x="sepal_length",
y="sepal_width",
z="petal_length",
color="class",
title="3-D Scatter Plot for sepal length, sepal width and petal length",
)
plot_4.show()
plot_5 = px.line_3d(
iris_df,
x="petal_width",
y="petal_length",
z="sepal_width",
hover_data=["sepal_length"],
color="class",
title="3-D Line Plot for all variables of all classes ",
)
plot_5.show()
# normalization, random forest and decision tree classifiers
x = iris_arr[:, 0:-1]
y = iris_df["class"].values
# pipeline_1 for random forest classifier
pipeline_1 = Pipeline(
[
("normalize", Normalizer()),
("randomforest", RandomForestClassifier(random_state=1234)),
]
)
print(pipeline_1.fit(x, y))
# pipeline_2 for decision tree classifier
pipeline_2 = Pipeline(
[
("normalize", Normalizer()),
("decisiontree", DecisionTreeClassifier()),
]
)
print(pipeline_2.fit(x, y))
if __name__ == "__main__":
sys.exit(main())
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
# assume you have a "long-form" data frame
# see https://plotly.com/python/px-arguments/ for more options
df = pd.read_csv(
'https://raw.githubusercontent.com/daniel-dc-cd/data_science/master/module_3_Python/data/titanic.csv'
)
df["Survived"] = df["Survived"].replace([0], "Didn't Survived")
df["Survived"] = df["Survived"].replace([1], "Did Survived")
fig1 = px.scatter(df, x="Age", y="Fare", color="Pclass", log_x=False)
fig2 = px.violin(df,
y="Age",
x="Survived",
color="Sex",
box=True,
points="all",
hover_data=df.columns)
fig3 = px.histogram(df, x="Survived", color="Pclass")
fig4 = px.histogram(df, x="Survived", color="Sex")
app.layout = html.Div(children=[
# All elements from the top of the page
html.Div([
html.H1(children='Yasir Alhejaili Project'),
html.Div(children='''
A scatter plot to see the relation between Age , Fare and each class
'''),
def return_tests_and_deaths_violin_figure(self, multiselection):
try:
import pandas as pd
import math
import plotly.express as px
from page_numbers_normalized_by_population import normalized_numbers_by_population_evolution as population_num
multiselection_tests_data = [
'United States' if x == 'US' else x for x in multiselection
]
selected_countries_tests_data = self.get_tests_evolution_data(
multiselection_tests_data)
not_nan_mask = pd.isna(
selected_countries_tests_data['Cumulative total per thousand']
) == False
selected_countries_tests_data = selected_countries_tests_data[
not_nan_mask]
selected_countries_tests_data[
'Cumulative total per thousand'] = selected_countries_tests_data[
'Cumulative total per thousand'].apply(
lambda x: int(x) if math.isnan(x) == False else x)
desired_cols = ['Date', 'Country', 'Cumulative total per thousand']
tests_sub_data = selected_countries_tests_data[desired_cols]
violin_tests_data = pd.DataFrame()
for country in tests_sub_data.Country.unique():
country_tests_violin_df = pd.DataFrame(columns=[
'Date', 'Country', 'Tests_per_thousand', 'Violin_color'
])
country_sub_data = tests_sub_data[tests_sub_data.Country ==
country]
for date in country_sub_data.Date:
country_date_tests_violin_df = pd.DataFrame(columns=[
'Date', 'Country', 'Tests_per_thousand', 'Violin_color'
])
country_sub_data_in_date = country_sub_data[
country_sub_data.Date == date]
cum_per_thousand_in_date = int(
country_sub_data_in_date.iloc[-1]
['Cumulative total per thousand'])
tests_dates = [
date for _ in range(cum_per_thousand_in_date)
]
country_date_tests_violin_df['Date'] = tests_dates
country_date_tests_violin_df['Country'] = country
country_date_tests_violin_df[
'Tests_per_thousand'] = cum_per_thousand_in_date
country_tests_violin_df = country_tests_violin_df.append(
country_date_tests_violin_df)
country_tests_violin_df[
'Violin_color'] = country_tests_violin_df[
'Tests_per_thousand'].max()
violin_tests_data = violin_tests_data.append(
country_tests_violin_df)
import numpy as np
import plotly.express as px
fig = px.violin(
violin_tests_data,
y="Date",
x="Country", #color=DEATH RATE
box=True,
hover_data=violin_tests_data.columns, #['Tests_per_thousand'],
title='Tests carried out per country',
color='Violin_color')
fig.update_layout(margin={
"r": 10,
"t": 60,
"l": 10,
"b": 10
},
height=600,
width=710,
showlegend=False,
paper_bgcolor="#EBF2EC")
return fig
except Exception as exc:
logger.exception('raised exception at {}: {}'.format(
logger.name + '.' + 'return_tests_and_deaths_figure', exc))
def build_graph(graph_type, x_axis, y_axis, color):
dff = df
if graph_type == 'LINE':
fig = px.line(dff, x=x_axis, y=y_axis, color=color, height=600)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'SCATTER':
fig = px.scatter(dff, x=x_axis, y=y_axis, color=color, height=600)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'BAR':
fig = px.bar(dff, x=x_axis, y=y_axis, color=color, height=600)
fig.update_xaxes(type='category')
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'AREA':
fig = px.area(dff, x=x_axis, y=y_axis, color=color, height=600)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'HEET':
fig = px.density_heatmap(dff,
x=x_axis,
y=y_axis,
nbinsx=20,
nbinsy=20,
marginal_x="histogram",
marginal="histogram")
elif graph_type == 'BOX':
fig = px.box(dff, x=x_axis, y=y_axis, color=color, height=600)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'PIE':
fig = px.pie(dff, values=x_axis, names=y_axis, height=600)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'HIST':
fig = px.histogram(dff,
x=x_axis,
y=y_axis,
marginal="box",
color=color,
height=600) # can be box or violin
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'SMX':
fig = px.scatter_matrix(dff, color=color)
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
elif graph_type == 'VIOLIN':
fig = px.violin(dff,
x=x_axis,
y=y_axis,
box=True,
color=color,
height=600) # can be box or violin
fig.update_layout(yaxis={'title': y_axis},
title={
'text': x_axis + ' vs ' + y_axis,
'font': {
'size': 28
},
'x': 0.5,
'xanchor': 'center'
})
return fig
def main():
side_img = Image.open("images/emotion3.jpg")
with st.sidebar:
st.image(side_img, width=300)
st.sidebar.subheader("Menu")
website_menu = st.sidebar.selectbox(
"Menu", ("Emotion Recognition", "Project description", "Our team",
"Leave feedback", "Relax"))
st.set_option('deprecation.showfileUploaderEncoding', False)
if website_menu == "Emotion Recognition":
st.sidebar.subheader("Model")
model_type = st.sidebar.selectbox("How would you like to predict?",
("mfccs", "mel-specs"))
em3 = em6 = em7 = gender = False
st.sidebar.subheader("Settings")
st.markdown("## Upload the file")
with st.container():
col1, col2 = st.columns(2)
# audio_file = None
# path = None
with col1:
audio_file = st.file_uploader("Upload audio file",
type=['wav', 'mp3', 'ogg'])
if audio_file is not None:
if not os.path.exists("audio"):
os.makedirs("audio")
path = os.path.join("audio", audio_file.name)
if_save_audio = save_audio(audio_file)
if if_save_audio == 1:
st.warning("File size is too large. Try another file.")
elif if_save_audio == 0:
# extract features
# display audio
st.audio(audio_file, format='audio/wav', start_time=0)
try:
wav, sr = librosa.load(path, sr=44100)
Xdb = get_melspec(path)[1]
mfccs = librosa.feature.mfcc(wav, sr=sr)
# # display audio
# st.audio(audio_file, format='audio/wav', start_time=0)
except Exception as e:
audio_file = None
st.error(
f"Error {e} - wrong format of the file. Try another .wav file."
)
else:
st.error("Unknown error")
else:
if st.button("Try test file"):
wav, sr = librosa.load("test.wav", sr=44100)
Xdb = get_melspec("test.wav")[1]
mfccs = librosa.feature.mfcc(wav, sr=sr)
# display audio
st.audio("test.wav", format='audio/wav', start_time=0)
path = "test.wav"
audio_file = "test"
with col2:
if audio_file is not None:
fig = plt.figure(figsize=(10, 2))
fig.set_facecolor('#d1d1e0')
plt.title("Wave-form")
librosa.display.waveplot(wav, sr=44100)
plt.gca().axes.get_yaxis().set_visible(False)
plt.gca().axes.get_xaxis().set_visible(False)
plt.gca().axes.spines["right"].set_visible(False)
plt.gca().axes.spines["left"].set_visible(False)
plt.gca().axes.spines["top"].set_visible(False)
plt.gca().axes.spines["bottom"].set_visible(False)
plt.gca().axes.set_facecolor('#d1d1e0')
st.write(fig)
else:
pass
# st.write("Record audio file")
# if st.button('Record'):
# with st.spinner(f'Recording for 5 seconds ....'):
# st.write("Recording...")
# time.sleep(3)
# st.success("Recording completed")
# st.write("Error while loading the file")
if model_type == "mfccs":
em3 = st.sidebar.checkbox("3 emotions", True)
em6 = st.sidebar.checkbox("6 emotions", True)
em7 = st.sidebar.checkbox("7 emotions")
gender = st.sidebar.checkbox("gender")
elif model_type == "mel-specs":
st.sidebar.warning("This model is temporarily disabled")
else:
st.sidebar.warning("This model is temporarily disabled")
# with st.sidebar.expander("Change colors"):
# st.sidebar.write("Use this options after you got the plots")
# col1, col2, col3, col4, col5, col6, col7 = st.columns(7)
#
# with col1:
# a = st.color_picker("Angry", value="#FF0000")
# with col2:
# f = st.color_picker("Fear", value="#800080")
# with col3:
# d = st.color_picker("Disgust", value="#A52A2A")
# with col4:
# sd = st.color_picker("Sad", value="#ADD8E6")
# with col5:
# n = st.color_picker("Neutral", value="#808080")
# with col6:
# sp = st.color_picker("Surprise", value="#FFA500")
# with col7:
# h = st.color_picker("Happy", value="#008000")
# if st.button("Update colors"):
# global COLOR_DICT
# COLOR_DICT = {"neutral": n,
# "positive": h,
# "happy": h,
# "surprise": sp,
# "fear": f,
# "negative": a,
# "angry": a,
# "sad": sd,
# "disgust": d}
# st.success(COLOR_DICT)
if audio_file is not None:
st.markdown("## Analyzing...")
if not audio_file == "test":
st.sidebar.subheader("Audio file")
file_details = {
"Filename": audio_file.name,
"FileSize": audio_file.size
}
st.sidebar.write(file_details)
with st.container():
col1, col2 = st.columns(2)
with col1:
fig = plt.figure(figsize=(10, 2))
fig.set_facecolor('#d1d1e0')
plt.title("MFCCs")
librosa.display.specshow(mfccs, sr=sr, x_axis='time')
plt.gca().axes.get_yaxis().set_visible(False)
plt.gca().axes.spines["right"].set_visible(False)
plt.gca().axes.spines["left"].set_visible(False)
plt.gca().axes.spines["top"].set_visible(False)
st.write(fig)
with col2:
fig2 = plt.figure(figsize=(10, 2))
fig2.set_facecolor('#d1d1e0')
plt.title("Mel-log-spectrogram")
librosa.display.specshow(Xdb,
sr=sr,
x_axis='time',
y_axis='hz')
plt.gca().axes.get_yaxis().set_visible(False)
plt.gca().axes.spines["right"].set_visible(False)
plt.gca().axes.spines["left"].set_visible(False)
plt.gca().axes.spines["top"].set_visible(False)
st.write(fig2)
if model_type == "mfccs":
st.markdown("## Predictions")
with st.container():
col1, col2, col3, col4 = st.columns(4)
mfccs = get_mfccs(path, model.input_shape[-1])
mfccs = mfccs.reshape(1, *mfccs.shape)
pred = model.predict(mfccs)[0]
with col1:
if em3:
pos = pred[3] + pred[5] * .5
neu = pred[2] + pred[5] * .5 + pred[4] * .5
neg = pred[0] + pred[1] + pred[4] * .5
data3 = np.array([pos, neu, neg])
txt = "MFCCs\n" + get_title(data3, CAT3)
fig = plt.figure(figsize=(5, 5))
COLORS = color_dict(COLOR_DICT)
plot_colored_polar(fig,
predictions=data3,
categories=CAT3,
title=txt,
colors=COLORS)
# plot_polar(fig, predictions=data3, categories=CAT3,
# title=txt, colors=COLORS)
st.write(fig)
with col2:
if em6:
txt = "MFCCs\n" + get_title(pred, CAT6)
fig2 = plt.figure(figsize=(5, 5))
COLORS = color_dict(COLOR_DICT)
plot_colored_polar(fig2,
predictions=pred,
categories=CAT6,
title=txt,
colors=COLORS)
# plot_polar(fig2, predictions=pred, categories=CAT6,
# title=txt, colors=COLORS)
st.write(fig2)
with col3:
if em7:
model_ = load_model("model4.h5")
mfccs_ = get_mfccs(path, model_.input_shape[-2])
mfccs_ = mfccs_.T.reshape(1, *mfccs_.T.shape)
pred_ = model_.predict(mfccs_)[0]
txt = "MFCCs\n" + get_title(pred_, CAT7)
fig3 = plt.figure(figsize=(5, 5))
COLORS = color_dict(COLOR_DICT)
plot_colored_polar(fig3,
predictions=pred_,
categories=CAT7,
title=txt,
colors=COLORS)
# plot_polar(fig3, predictions=pred_, categories=CAT7,
# title=txt, colors=COLORS)
st.write(fig3)
with col4:
if gender:
with st.spinner('Wait for it...'):
gmodel = load_model("model_mw.h5")
gmfccs = get_mfccs(path,
gmodel.input_shape[-1])
gmfccs = gmfccs.reshape(1, *gmfccs.shape)
gpred = gmodel.predict(gmfccs)[0]
gdict = [["female", "woman.png"],
["male", "man.png"]]
ind = gpred.argmax()
txt = "Predicted gender: " + gdict[ind][0]
img = Image.open("images/" + gdict[ind][1])
fig4 = plt.figure(figsize=(3, 3))
fig4.set_facecolor('#d1d1e0')
plt.title(txt)
plt.imshow(img)
plt.axis("off")
st.write(fig4)
# if model_type == "mel-specs":
# st.markdown("## Predictions")
# st.warning("The model in test mode. It may not be working properly.")
# if st.checkbox("I'm OK with it"):
# try:
# with st.spinner("Wait... It can take some time"):
# global tmodel
# tmodel = load_model_cache("tmodel_all.h5")
# fig, tpred = plot_melspec(path, tmodel)
# col1, col2, col3 = st.columns(3)
# with col1:
# st.markdown("### Emotional spectrum")
# dimg = Image.open("images/spectrum.png")
# st.image(dimg, use_column_width=True)
# with col2:
# fig_, tpred_ = plot_melspec(path=path,
# tmodel=tmodel,
# three=True)
# st.write(fig_, use_column_width=True)
# with col3:
# st.write(fig, use_column_width=True)
# except Exception as e:
# st.error(f"Error {e}, model is not loaded")
elif website_menu == "Project description":
import pandas as pd
import plotly.express as px
st.title("Project description")
st.subheader("GitHub")
link = '[GitHub repository of the web-application]' \
'(https://github.com/CyberMaryVer/speech-emotion-webapp)'
st.markdown(link, unsafe_allow_html=True)
st.subheader("Theory")
link = '[Theory behind - Medium article]' \
'(https://talbaram3192.medium.com/classifying-emotions-using-audio-recordings-and-python-434e748a95eb)'
st.markdown(link + ":clap::clap::clap: Tal!", unsafe_allow_html=True)
with st.expander("See Wikipedia definition"):
components.iframe(
"https://en.wikipedia.org/wiki/Emotion_recognition",
height=320,
scrolling=True)
st.subheader("Dataset")
txt = """
This web-application is a part of the final **Data Mining** project for **ITC Fellow Program 2020**.
Datasets used in this project
* Crowd-sourced Emotional Mutimodal Actors Dataset (**Crema-D**)
* Ryerson Audio-Visual Database of Emotional Speech and Song (**Ravdess**)
* Surrey Audio-Visual Expressed Emotion (**Savee**)
* Toronto emotional speech set (**Tess**)
"""
st.markdown(txt, unsafe_allow_html=True)
df = pd.read_csv("df_audio.csv")
fig = px.violin(df,
y="source",
x="emotion4",
color="actors",
box=True,
points="all",
hover_data=df.columns)
st.plotly_chart(fig, use_container_width=True)
st.subheader("FYI")
st.write(
"Since we are currently using a free tier instance of AWS, "
"we disabled mel-spec and ensemble models.\n\n"
"If you want to try them we recommend to clone our GitHub repo")
st.code(
"git clone https://github.com/CyberMaryVer/speech-emotion-webapp.git",
language='bash')
st.write(
"After that, just uncomment the relevant sections in the app.py file "
"to use these models:")
elif website_menu == "Our team":
st.subheader("Our team")
st.balloons()
col1, col2 = st.columns([3, 2])
with col1:
st.info("*****@*****.**")
st.info("*****@*****.**")
st.info("*****@*****.**")
with col2:
liimg = Image.open("images/LI-Logo.png")
st.image(liimg)
st.markdown(
f""":speech_balloon: [Maria Startseva](https://www.linkedin.com/in/maria-startseva)""",
unsafe_allow_html=True)
st.markdown(
f""":speech_balloon: [Tal Baram](https://www.linkedin.com/in/tal-baram-b00b66180)""",
unsafe_allow_html=True)
st.markdown(
f""":speech_balloon: [Asher Holder](https://www.linkedin.com/in/asher-holder-526a05173)""",
unsafe_allow_html=True)
elif website_menu == "Leave feedback":
st.subheader("Leave feedback")
user_input = st.text_area("Your feedback is greatly appreciated")
user_name = st.selectbox(
"Choose your personality",
["checker1", "checker2", "checker3", "checker4"])
if st.button("Submit"):
st.success(f"Message\n\"\"\"{user_input}\"\"\"\nwas sent")
if user_input == "log123456" and user_name == "checker4":
with open("log0.txt", "r", encoding="utf8") as f:
st.text(f.read())
elif user_input == "feedback123456" and user_name == "checker4":
with open("log.txt", "r", encoding="utf8") as f:
st.text(f.read())
else:
log_file(user_name + " " + user_input)
thankimg = Image.open("images/sticky.png")
st.image(thankimg)
else:
import requests
import json
url = 'http://api.quotable.io/random'
if st.button("get random mood"):
with st.container():
col1, col2 = st.columns(2)
n = np.random.randint(1, 1000, 1)[0]
with col1:
quotes = {
"Good job and almost done":
"checker1",
"Great start!!":
"checker2",
"Please make corrections base on the following observation":
"checker3",
"DO NOT train with test data":
"folk wisdom",
"good work, but no docstrings":
"checker4",
"Well done!":
"checker3",
"For the sake of reproducibility, I recommend setting the random seed":
"checker1"
}
if n % 5 == 0:
a = np.random.choice(list(quotes.keys()), 1)[0]
quote, author = a, quotes[a]
else:
try:
r = requests.get(url=url)
text = json.loads(r.text)
quote, author = text['content'], text['author']
except Exception as e:
a = np.random.choice(list(quotes.keys()), 1)[0]
quote, author = a, quotes[a]
st.markdown(f"## *{quote}*")
st.markdown(f"### ***{author}***")
with col2:
st.image(image=f"https://picsum.photos/800/600?random={n}")
def main():
columns = ["Sepal_Length", "Sepal_Width", "Petal_Length", "Petal_Width", "Species"]
iris_data = pd.read_csv("Iris.data", names=columns)
print(iris_data.head(10))
print(iris_data.info())
# getting the number of missing values
missing = iris_data.isnull().sum()
print(missing)
# calculating the summary statistics
print("Mean statistics:", np.mean(iris_data))
print("Maximum value:", np.max(iris_data))
print("Minimum value:", np.min(iris_data))
# Calculating quantiles
iris_np = np.array(iris_data)
print("25 percent- ", np.quantile(iris_np[:, :-1], 0.25, axis=0))
print("50 percent-", np.quantile(iris_np[:, :-1], 0.50, axis=0))
print("75 percent-", np.quantile(iris_np[:, :-1], 0.75, axis=0))
# Visualizing the data
plot1 = px.violin(
iris_data,
y="Sepal_Length",
x="Species",
color="Species",
hover_data=iris_data.columns,
title="Violin plot to visualize Sepal Length ",
)
plot1.show()
plot2 = px.scatter_3d(
iris_data,
x="Sepal_Width",
y="Sepal_Length",
z="Petal_Width",
color="Species",
hover_data=iris_data.columns,
title="3d Scatter plot between Sepal Width, " "Sepal length and Petal width",
)
plot2.show()
plot3 = px.histogram(
iris_data,
x="Sepal_Length",
y="Sepal_Width",
color="Species",
title="Distribution of Sepal length and Sepal width with respect to species",
)
plot3.show()
iris_data.plot(kind="scatter", x="Sepal_Length", y="Petal_Length")
plt.title("Scatter plot between Sepal Length and petal Length")
plt.show()
sns.set_style("whitegrid")
sns.FacetGrid(iris_data, hue="Species", height=6).map(
plt.scatter, "Sepal_Length", "Petal_Length"
).add_legend()
plt.title(
"Scatter plot between Sepal Length and Petal Length, with different species"
)
plt.show()
# Splitting the dataset into train and test
X_train, X_test, y_train, y_test = train_test_split(
iris_data.iloc[:, :-1].values,
iris_data["Species"],
test_size=0.2,
random_state=1234,
)
# Making a Pipeline for Normalizing the data and fitting RandomForestClassifier
pipeline = Pipeline(
[("Normalize", Normalizer()), ("rf", RandomForestClassifier(random_state=1234))]
)
pipeline.fit(X_train, y_train)
predict = pipeline.predict(X_test)
# Generating the confusion matrix and accuracy score for the RandomForestClassifier
cm = confusion_matrix(y_test, predict)
print("Confusion Matrix- RandomForestClassifier", cm)
accuracy = accuracy_score(y_test, predict)
print("Accuracy of RandomForestClassifier", accuracy)
# Making a pipeline for Normalizing the data and fitting LDAClassifier
pipeline = Pipeline([("Normalize", Normalizer()), ("lda", LDA(n_components=1))])
pipeline.fit(X_train, y_train)
predict = pipeline.predict(X_test)
# Generating the confusion matrix and accuracy score for the LDAClassifier
cm = confusion_matrix(y_test, predict)
print("Confusion Matrix- LDAClassifier", cm)
accuracy = accuracy_score(y_test, predict)
print("Accuracy of LDAClassifier", accuracy)
!pip install sweetviz import sweetviz as sv my_report = sv.analyze(dataset[['profit', 'sales', 'Cost', 'quantity']].sample(frac=0.2)) my_report.show_notebook() country = dataset.loc[dataset.country.isin(['Germany', 'United Kingdom'])] sns.countplot(y='country', data=country, order=['Germany', 'United Kingdom'], palette=['Red', 'yellow']) plt.show() # country['country'].value_counts().index """# Plotly Express""" import plotly.express as px fig = px.violin(dataset, y='sales', x='ship_mode') fig.show() country = dataset.groupby(['country']).sum()['quantity'].reset_index() px.bar(country, x='country', y='quantity').show() """# Folium""" import folium dataset.head() m = folium.Map(location=[49.006890, 8.403653]) m
def plot_graphs(request):
print("plot_graphs function")
global ppd
fig = None
fig_error = False
blank_choice = (None, '---------')
features_name = [(i, i) for i in ppd.getFeatureName()]
category_features_name = [(i, i) for i in ppd.get_category_list()]
numeric_features_name = [(i, i) for i in ppd.get_numeric_features_name()]
features_name.append(blank_choice)
category_features_name.append(blank_choice)
numeric_features_name.append(blank_choice)
if request.method == 'POST':
if 'scatter_btn' in request.POST:
print("scatter form")
print(request.POST)
scatter = Scatter_form(request.POST)
scatter.fields['x'].choices = features_name
scatter.fields['y'].choices = features_name
scatter.fields['facet_row'].choices = category_features_name
scatter.fields['facet_col'].choices = category_features_name
scatter.fields['color'].choices = category_features_name
scatter.fields['size'].choices = numeric_features_name
print(scatter.errors)
if scatter.is_valid():
print("form valid")
x = scatter.cleaned_data['x']
y = scatter.cleaned_data['y']
facet_row = scatter.cleaned_data['facet_row']
facet_col = scatter.cleaned_data['facet_col']
facet_col_wrap = scatter.cleaned_data['facet_col_wrap']
color = scatter.cleaned_data['color']
size = scatter.cleaned_data['size']
data_feature_list = list()
data_feature_list.append(x)
data_feature_list.append(y)
if len(size) > 0:
data_feature_list.append(size)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.scatter(
data_frame=data,
x=x,
y=y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=scatter.cleaned_data['title'],
color=None if len(color) == 0 else color,
size=None if len(size) == 0 else size,
log_x=scatter.cleaned_data['log_x'],
log_y=scatter.cleaned_data['log_y'],
render_mode=scatter.cleaned_data['render_mode'],
height=800)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'scatter_3d_btn' in request.POST:
scatter_3d = Scatter_3d_form(request.POST)
scatter_3d.fields['x'].choices = features_name
scatter_3d.fields['y'].choices = features_name
scatter_3d.fields['z'].choices = features_name
scatter_3d.fields['color'].choices = category_features_name
scatter_3d.fields['size'].choices = numeric_features_name
if scatter_3d.is_valid():
x = scatter_3d.cleaned_data['x']
y = scatter_3d.cleaned_data['y']
z = scatter_3d.cleaned_data['z']
color = scatter_3d.cleaned_data['color']
size = scatter_3d.cleaned_data['size']
data_feature_list = list()
data_feature_list.append(x)
data_feature_list.append(y)
data_feature_list.append(z)
if len(size) > 0:
data_feature_list.append(size)
if len(color) > 0:
data_feature_list.append(color)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.scatter_3d(
data_frame=data,
x=x,
y=y,
z=z,
title=scatter_3d.cleaned_data['title'],
color=None if len(color) == 0 else color,
size=None if len(size) == 0 else size,
log_x=scatter_3d.cleaned_data['log_x'],
log_y=scatter_3d.cleaned_data['log_y'],
log_z=scatter_3d.cleaned_data['log_z'],
height=800)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'line_btn' in request.POST:
print("Line Plot")
line = Line_form(request.POST)
line.fields['x'].choices = features_name
line.fields['y'].choices = features_name
line.fields['facet_row'].choices = category_features_name
line.fields['facet_col'].choices = category_features_name
line.fields['color'].choices = category_features_name
if line.is_valid():
print("line is valid")
x = line.cleaned_data['x']
y = line.cleaned_data['y']
facet_row = line.cleaned_data['facet_row']
facet_col = line.cleaned_data['facet_col']
facet_col_wrap = line.cleaned_data['facet_col_wrap']
color = line.cleaned_data['color']
data_feature_list = list()
data_feature_list.append(x)
data_feature_list.append(y)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.line(
data_frame=data,
x=x,
y=y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=line.cleaned_data['title'],
color=None if len(color) == 0 else color,
height=800)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'bar_btn' in request.POST:
print("Bar Plot")
bar = Bar_form(request.POST)
bar.fields['x'].choices = features_name
bar.fields['y'].choices = features_name
bar.fields['facet_row'].choices = category_features_name
bar.fields['facet_col'].choices = category_features_name
bar.fields['color'].choices = category_features_name
if bar.is_valid():
print("Bar is valid")
x = bar.cleaned_data['x']
y = bar.cleaned_data['y']
facet_row = bar.cleaned_data['facet_row']
facet_col = bar.cleaned_data['facet_col']
facet_col_wrap = bar.cleaned_data['facet_col_wrap']
color = bar.cleaned_data['color']
title = bar.cleaned_data['title']
orientation = bar.cleaned_data['orientation']
bar_mode = bar.cleaned_data['bar_mode']
data_feature_list = list()
data_feature_list.append(x)
data_feature_list.append(y)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.bar(
data_frame=data,
x=x,
y=y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=title,
color=None if len(color) == 0 else color,
orientation=orientation,
barmode=bar_mode,
height=800)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'pie_btn' in request.POST:
print("Pie Plot")
pie = Pie_form(request.POST)
pie.fields['values'].choices = features_name
pie.fields['names'].choices = category_features_name
pie.fields['color'].choices = category_features_name
if pie.is_valid():
print("Pie is valid")
values = pie.cleaned_data['values']
names = pie.cleaned_data['names']
color = pie.cleaned_data['color']
title = pie.cleaned_data['title']
data_feature_list = list()
data_feature_list.append(values)
data_feature_list.append(names)
if len(color) > 0:
data_feature_list.append(color)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.pie(data_frame=data,
values=values,
names=names,
color=None if len(color) == 0 else color,
title=title,
height=800)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'histogram_btn' in request.POST:
print("Plot Histogram")
histogram = Histogram_form(request.POST)
histogram.fields['x'].choices = features_name
histogram.fields['y'].choices = features_name
histogram.fields['facet_row'].choices = category_features_name
histogram.fields['facet_col'].choices = category_features_name
histogram.fields['color'].choices = category_features_name
print(histogram.errors)
if histogram.is_valid():
print("Histogram is valid")
x = histogram.cleaned_data['x']
y = histogram.cleaned_data['y']
facet_row = histogram.cleaned_data['facet_row']
facet_col = histogram.cleaned_data['facet_col']
facet_col_wrap = histogram.cleaned_data['facet_col_wrap']
color = histogram.cleaned_data['color']
title = histogram.cleaned_data['title']
orientation = histogram.cleaned_data['orientation']
bar_mode = histogram.cleaned_data['bar_mode']
marginal = histogram.cleaned_data['marginal']
bar_norm = histogram.cleaned_data['bar_norm']
hist_norm = histogram.cleaned_data['hist_norm']
hist_func = histogram.cleaned_data['hist_func']
log_x = histogram.cleaned_data['log_x']
log_y = histogram.cleaned_data['log_y']
cumulative = histogram.cleaned_data['cumulative']
data_feature_list = list()
data_feature_list.append(x)
data_feature_list.append(y)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.histogram(
data_frame=data,
x=x,
y=y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=title,
color=None if len(color) == 0 else color,
orientation=orientation,
barmode=bar_mode,
marginal=marginal,
barnorm=bar_norm,
histnorm=hist_norm,
histfunc=hist_func,
log_x=log_x,
log_y=log_y,
cumulative=cumulative,
height=800)
print("Fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'scatter_matrix_btn' in request.POST:
print("Scatter Matrix Plot")
scatter_matrix = Scatter_matrix_form(request.POST)
scatter_matrix.fields['feature_1'].choices = numeric_features_name
scatter_matrix.fields['feature_2'].choices = numeric_features_name
scatter_matrix.fields['feature_3'].choices = numeric_features_name
scatter_matrix.fields['feature_4'].choices = numeric_features_name
scatter_matrix.fields['color'].choices = category_features_name
scatter_matrix.fields['size'].choices = numeric_features_name
scatter_matrix.fields['symbol'].choices = category_features_name
if scatter_matrix.is_valid():
print("Scatter Matrix is valid")
feature_1 = scatter_matrix.cleaned_data['feature_1']
feature_2 = scatter_matrix.cleaned_data['feature_2']
feature_3 = scatter_matrix.cleaned_data['feature_3']
feature_4 = scatter_matrix.cleaned_data['feature_4']
color = scatter_matrix.cleaned_data['color']
symbol = scatter_matrix.cleaned_data['symbol']
size = scatter_matrix.cleaned_data['size']
title = scatter_matrix.cleaned_data['title']
data_feature_list = list()
data_feature_list.append(feature_1)
data_feature_list.append(feature_2)
data_feature_list.append(feature_3)
data_feature_list.append(feature_4)
if len(size) > 0:
data_feature_list.append(size)
if len(color) > 0:
data_feature_list.append(color)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.scatter_matrix(
data_frame=data,
dimensions=[
feature_1, feature_2, feature_3, feature_4
],
color=None if len(color) == 0 else color,
symbol=None if len(symbol) == 0 else symbol,
size=None if len(size) == 0 else size,
title=title)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'box_btn' in request.POST:
box = Box_form(request.POST)
box.fields['x'].choices = features_name
box.fields['y'].choices = features_name
box.fields['facet_row'].choices = category_features_name
box.fields['facet_col'].choices = category_features_name
box.fields['color'].choices = category_features_name
print(box.errors)
if box.is_valid():
x = box.cleaned_data['x']
y = box.cleaned_data['y']
facet_row = box.cleaned_data['facet_row']
facet_col = box.cleaned_data['facet_col']
color = box.cleaned_data['color']
facet_col_wrap = box.cleaned_data['facet_col_wrap']
title = box.cleaned_data['title']
orientation = box.cleaned_data['orientation']
log_x = box.cleaned_data['log_x']
log_y = box.cleaned_data['log_y']
box_mode = box.cleaned_data['box_mode']
points = box.cleaned_data['points']
notched = box.cleaned_data['notched']
data_feature_list = list()
if len(x) > 0:
data_feature_list.append(x)
if len(y) > 0:
data_feature_list.append(y)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.box(
data_frame=data,
x=None if len(x) == 0 else x,
y=None if len(y) == 0 else y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=title,
orientation=orientation,
log_x=log_x,
log_y=log_y,
boxmode=box_mode,
points=points,
notched=notched)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'violin_btn' in request.POST:
violin = Violin_form(request.POST)
violin.fields['x'].choices = features_name
violin.fields['y'].choices = features_name
violin.fields['facet_row'].choices = category_features_name
violin.fields['facet_col'].choices = category_features_name
violin.fields['color'].choices = category_features_name
print(violin.errors)
if violin.is_valid():
x = violin.cleaned_data['x']
y = violin.cleaned_data['y']
facet_row = violin.cleaned_data['facet_row']
facet_col = violin.cleaned_data['facet_col']
color = violin.cleaned_data['color']
facet_col_wrap = violin.cleaned_data['facet_col_wrap']
title = violin.cleaned_data['title']
orientation = violin.cleaned_data['orientation']
log_x = violin.cleaned_data['log_x']
log_y = violin.cleaned_data['log_y']
violin_mode = violin.cleaned_data['violin_mode']
points = violin.cleaned_data['points']
box = violin.cleaned_data['box']
data_feature_list = list()
if len(x) > 0:
data_feature_list.append(x)
if len(y) > 0:
data_feature_list.append(y)
if len(color) > 0:
data_feature_list.append(color)
if len(facet_row) > 0:
data_feature_list.append(facet_row)
if len(facet_col) > 0:
data_feature_list.append(facet_col)
data = pd.DataFrame(ppd.get_features_data(data_feature_list))
try:
fig = px.violin(
data_frame=data,
x=None if len(x) == 0 else x,
y=None if len(y) == 0 else y,
facet_row=None if len(facet_row) == 0 else facet_row,
facet_col=None if len(facet_col) == 0 else facet_col,
facet_col_wrap=facet_col_wrap,
title=title,
orientation=orientation,
log_x=log_x,
log_y=log_y,
violinmode=violin_mode,
points=points,
box=box)
print("fig create success")
except:
print("fig create error")
fig_error = True
fig = None
if 'heat_map_btn' in request.POST:
print("Heat Map")
heat_map_data = pd.DataFrame(ppd.get_corr_matrix())
print(heat_map_data.columns)
try:
fig = px.imshow(heat_map_data.astype(float),
x=heat_map_data.columns,
y=heat_map_data.index,
zmax=1,
zmin=-1,
height=800)
except:
print("fig create error")
fig_error = True
fig = None
scatter = Scatter_form()
scatter.fields['x'].choices = features_name
scatter.fields['y'].choices = features_name
scatter.fields['facet_row'].choices = category_features_name
scatter.fields['facet_col'].choices = category_features_name
scatter.fields['color'].choices = category_features_name
scatter.fields['size'].choices = numeric_features_name
scatter_3d = Scatter_3d_form()
scatter_3d.fields['x'].choices = features_name
scatter_3d.fields['y'].choices = features_name
scatter_3d.fields['z'].choices = features_name
scatter_3d.fields['color'].choices = category_features_name
scatter_3d.fields['size'].choices = numeric_features_name
line = Line_form()
line.fields['x'].choices = features_name
line.fields['y'].choices = features_name
line.fields['facet_row'].choices = category_features_name
line.fields['facet_col'].choices = category_features_name
line.fields['color'].choices = category_features_name
bar = Bar_form()
bar.fields['x'].choices = features_name
bar.fields['y'].choices = features_name
bar.fields['facet_row'].choices = category_features_name
bar.fields['facet_col'].choices = category_features_name
bar.fields['color'].choices = category_features_name
pie = Pie_form()
pie.fields['values'].choices = features_name
pie.fields['names'].choices = category_features_name
pie.fields['color'].choices = category_features_name
histogram = Histogram_form()
histogram.fields['x'].choices = features_name
histogram.fields['y'].choices = features_name
histogram.fields['facet_row'].choices = category_features_name
histogram.fields['facet_col'].choices = category_features_name
histogram.fields['color'].choices = category_features_name
scatter_matrix = Scatter_matrix_form()
scatter_matrix.fields['feature_1'].choices = numeric_features_name
scatter_matrix.fields['feature_2'].choices = numeric_features_name
scatter_matrix.fields['feature_3'].choices = numeric_features_name
scatter_matrix.fields['feature_4'].choices = numeric_features_name
scatter_matrix.fields['color'].choices = category_features_name
scatter_matrix.fields['size'].choices = numeric_features_name
scatter_matrix.fields['symbol'].choices = category_features_name
box = Box_form()
box.fields['x'].choices = features_name
box.fields['y'].choices = features_name
box.fields['facet_row'].choices = category_features_name
box.fields['facet_col'].choices = category_features_name
box.fields['color'].choices = category_features_name
violin = Violin_form()
violin.fields['x'].choices = features_name
violin.fields['y'].choices = features_name
violin.fields['facet_row'].choices = category_features_name
violin.fields['facet_col'].choices = category_features_name
violin.fields['color'].choices = category_features_name
context = {
'fig': None,
'scatter': scatter,
'line': line,
'scatter_3d': scatter_3d,
'bar': bar,
'pie': pie,
'histogram': histogram,
'scatter_matrix': scatter_matrix,
'box': box,
'violin': violin
}
if fig is not None:
context['fig'] = pio.to_html(fig=fig,
full_html=False,
include_plotlyjs=False)
elif fig_error is True:
context[
'fig'] = "Plot Graph Error When Setting Parameters. Please Try Again!"
else:
context['fig'] = None
return render(request,
'data_cleaning_app/plot_graphs.html',
context=context)