def main():
menu = ['Pandas-Profiling', 'SweetViz', 'D-tale', 'About']
option = st.selectbox("Select Tool for Viz", menu)
if option == 'Pandas-Profiling':
st.header("Pandas-Profiling")
data_file = st.file_uploader("Upload_csv", type=['csv'])
if data_file is not None:
load_csv = pd.read_csv(data_file)
st.write(load_csv.head())
st.success("Successfully uploaded!")
if st.button('Generate Report'):
report = ProfileReport(load_csv,
title="CSV Profiling Report",
explorative=True)
st.write('---')
st.header('**Pandas Profiling Report**')
st_profile_report(report)
elif option == 'SweetViz':
st.header("SweetViz")
data_file = st.file_uploader("Upload_csv", type=['csv'])
st.success("Successfully uploaded!")
if data_file is not None:
load_csv = pd.read_csv(data_file)
st.write(load_csv)
st.write('---')
st.header('**SweetViz Profiling Report**')
if st.button('Generate Report'):
report = sv.analyze(load_csv)
report.show_html()
display_sweetviz("SWEETVIZ_REPORT.html")
elif option == 'D-tale':
st.header('D-tale')
data_file = st.file_uploader("Upload_csv", type=['csv'])
st.success("Successfully uploaded!")
if data_file is not None:
load_csv = pd.read_csv(data_file)
st.write(load_csv)
st.write('---')
st.header('**D-Tale Profiling Report**')
if st.button('Generate Report'):
dtale.show(load_csv)
components.iframe('http://dell-virlgti:40000/dtale/main/1',
width=1500,
height=800,
scrolling=True)
# st.markdown(html, unsafe_allow_html=True)
elif menu == 'About':
st.subheader(
"Simple tool for better and quick visualization and EDA!!")
st.write()
st.write(
"check out this [link](https://share.streamlit.io/mesmith027/streamlit_webapps/main/MC_pi/streamlit_app.py)"
)
def display_data():
data = data_loader.get_data()
d = dtale.show(data, host="localhost", open_browser=True)
print("Hit enter to exit.")
input()
print("Exiting...")
d.kill()
def _dtale_show(self, *args, **kwargs) -> dtale.views.DtaleData:
result = dtale.show(*args, **kwargs)
if self._first_show:
# when running show for the first time, if that happens in rapid succession, it can cause race conditions
# internal to dtale
time.sleep(0.3)
self._first_show = False
return result
def displaydata(self):
#print(self.triggerData)
df = pd.DataFrame.from_dict(self.triggerData).T
d = dtale.show(df, ignore_duplicate=True)
d.open_browser()
print(d._url)
file1 = open('triggers.txt','w')
file1.write(str(self.triggerData))
def backTestPatterns(self):
patternReturns = {}
for s in self.symboldata:
print(s)
for pattern in self.symboldata[s]:
if(s == self.symbols[0]):
patternReturns[pattern] = {}
patternReturns[pattern]['POS'] = 0
patternReturns[pattern]['NEG'] = 0
patternReturns[pattern]['DATA'] = 0
Postriggers = 0
Posreturns = 0
Negstriggers = 0
Negreturns = 0
for date, value in self.symboldata[s][pattern].iteritems():
try:
if(value==0):
continue
#print(str(date).split(' ')[0])
#print(str(datetime.datetime.today()).split(' ')[0])
if(str(date).split(' ')[0] == str(datetime.datetime.today()).split(' ')[0]):
continue
if (value>0):
Postriggers = Postriggers + 1
tickerData = yfinance.Ticker(s)
triggerPrice = self.tickerDf[s].close[str(date)]
nextDayPrice = self.tickerDf[s].close[str(date+datetime.timedelta(days=1)).split(' ')[0]]
Posreturns += (nextDayPrice/triggerPrice-1)*100
if (value<0):
Negstriggers = Negstriggers + 1
tickerData = yfinance.Ticker(s)
triggerPrice = self.tickerDf[s].close[str(date)]
nextDayPrice = self.tickerDf[s].close[str(date+datetime.timedelta(days=1)).split(' ')[0]]
Negreturns += (nextDayPrice/triggerPrice-1)*100
except:
continue
if not (Postriggers==0):
patternReturns[pattern]['POS'] += Posreturns/Postriggers
patternReturns[pattern]['DATA'] += Postriggers
if not (Negstriggers==0):
patternReturns[pattern]['NEG'] += Negreturns/Negstriggers
patternReturns[pattern]['DATA'] += Negstriggers
for pattern in patternReturns:
patternReturns[pattern]['POS'] = patternReturns[pattern]['POS']/len(self.symbols)
patternReturns[pattern]['NEG'] = patternReturns[pattern]['NEG']/len(self.symbols)
df = pd.DataFrame.from_dict(patternReturns).T
d = dtale.show(df, ignore_duplicate=True)
d.open_browser()
print(patternReturns)
autos = autos[autos["registration_year"].between(1900, 2016)] # In[14]: #Inspecting the data statistics after removal of above identified rows autos.describe() # In[15]: #Inpscting the "registration_year" column in more detail, specifically getting the value_counts and estimating the most common year. autos["registration_year"].value_counts(normalize=True) # In[16]: dtale.show(autos) # **Write a summary of the above steps, as in the removal of outliers and the calculation of value counts for the registration year.** # **The next section of analysis could essentially focus on the estimation of mean price and mileage across brands** # # - We will group (Aggregate the data) across the most common brands, create dictionaries for each of the variables and save the values # # # In[17]: count_of_brands = autos["brand"].value_counts(normalize=True) #Restricting the above analysis to the top 5% of the brands, would be a reasonable assumption here
import pandas as pd
import dtale
data = pd.read_excel("YOUR_FILE_PATH.xlsx")
d= dtale.show(data)
d.open_browser()
sweet_report1 = sv.analyze(df_hospital)
sweet_report1.show_html('/Users/hantswilliams/Dropbox/Biovirtua/Python_Projects/ahi/AHI_STATS_507/Week13_Summary/output/sweet_report_df_hospital.html')
sweet_report2 = sv.analyze(df_outpatient)
sweet_report2.show_html('/Users/hantswilliams/Dropbox/Biovirtua/Python_Projects/ahi/AHI_STATS_507/Week13_Summary/output/sweet_report_df_outpatient.html')
sweet_report3 = sv.analyze(df_inpatient)
sweet_report3.show_html('/Users/hantswilliams/Dropbox/Biovirtua/Python_Projects/ahi/AHI_STATS_507/Week13_Summary/output/sweet_report_df_inpatient.html')
# D-tale
import dtale
d = dtale.show(df_hospital, ignore_duplicate=True)
d.open_browser()
########################################################################################################################
########################################################################################################################
########################################################################################################################
########################################################################################################################
########################################################################################################################
########################################################################################################################
### Automatic Data Cleaning
wearables_data_url = 'https://raw.githubusercontent.com/programmablewealth/aavegotchi-stats/master/src/data/wearables/wearables.json'
wearables_data = requests.get(wearables_data_url).json()
wearables_name = {i: wearables_data[str(i)]["0"] for i in wearables_data}
gotchi_sales['Body Item'] = gotchi_sales['Body'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Face Item'] = gotchi_sales['Face'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Eyes Item'] = gotchi_sales['Eyes'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Head Item'] = gotchi_sales['Head'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Left Hand Item'] = gotchi_sales['Left Hand'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Right Hand Item'] = gotchi_sales['Right Hand'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Pet Item'] = gotchi_sales['Pet'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
gotchi_sales['Background Item'] = gotchi_sales['Background'].apply(
lambda x: 'NaN' if x == 0 else wearables_data[str(x)]["0"])
#%%
#%%
gotchi_sales.to_csv('gotchi.csv')
# %%
import dtale
d = dtale.show(gotchi_sales)
d
# %%
import pandas as pd
symbol="SPY"
period= 1
# GET SYMBOL CALLS
def getOptionCalls(symbol,period):
try:
ticker = yf.Ticker(symbol)
#Expiration periods ex: 1 is the first expiration period
optionChain = ticker.option_chain(ticker.options[period])
optionCalls = optionChain[0]
return optionCalls
except NameError:
return NameError
# GET SYMBOL PUTS
def getOptionPuts(symbol,period):
try:
ticker = yf.Ticker(symbol)
#Expiration periods ex: 1 is the first expiration period
optionChain = ticker.option_chain(ticker.options[period])
optionPuts= optionChain[1]
return optionPuts
except NameError:
return NameError
options=getOptionPuts(symbol,period)
d= dtale.show(options)
d.open_browser()
fig.add_annotation(
dict(xref='paper',
yref='paper',
x=0.01,
y=0.02,
xanchor='left',
yanchor='middle',
font=dict(family='Arial', size=14, color='purple'),
showarrow=False,
text='Dismissed'))
fig.show()
# dtale eds
# pip install dtale
import dtale
d = dtale.show(departures)
d.open_browser()
# pandas-profiling
# pip install pandas-profiling
import pandas_profiling
pandas_profiling.ProfileReport(departures)
# AutoViz
from autoviz.AutoViz_Class import AutoViz_Class
AV = AutoViz_Class()
sep = ','
dft = AV.AutoViz(filename="",
sep=sep,
depVar='fyear',
#https://github.com/man-group/dtale
#pip install dtale
#pip install yfinance
import dtale
import yfinance as yf
def getSymbolHistoricalPrice(tickerSymbol):
try:
ticker = yf.Ticker(tickerSymbol)
tickerHistPrice = ticker.history("max")
return tickerHistPrice
except NameError:
return NameError
ticker = "SPY"
dfQuoteData = getSymbolHistoricalPrice(ticker)
d = dtale.show(dfQuoteData)
d.open_browser()
from pandas_profiling import ProfileReport
#profile = ProfileReport(df, title="Tips Dataset", html={'style': {'full_width': True}}, sort="None")
profile = ProfileReport(df) # for large dataset (minimal=True)
profile.to_notebook_iframe()
#profile.to_file(output_file="your_report.html")
# For Jupyter Notebook
from pandas_profiling import ProfileReport
profile = ProfileReport(df, explorative=True, minimal = True)
profile.to_file('output.html')
### Dtale (EDA)
# For Spyder
import dtale
import plotly.express as px
d = dtale.show(df, ignore_duplicate=True)
d.open_browser()
# For Jupyter Notebook
import dtale
dtale.show(df)
### Pandas_ui
import seaborn as sns
df = sns.load_dataset("tips")
from pandas_ui import *
pandas_ui('D:\\KNOWLEDGE KORNER\\ANALYTICS\\MISC\\Practice\\Kaggle & Hackathons\\Tips\\tips.csv')
#==============================================================================
### Upload CSV Files
import pandas as pd
titanic = pd.read_csv('titanic.csv')
print(titanic.head)
#Data EDA in two lines of code using pandas_profiling
import pandas_profiling as pp
profile = pp.ProfileReport(titanic, explorative=True)
profile.to_file('output.html')
#EDA using Sweetviz
import sweetviz as sv
sweet_report = sv.analyze(titanic)
sweet_report.show_html('sweet_report.html')
#EDA using Autoviz
from autoviz.AutoViz_Class import AutoViz_Class
aviz = AutoViz_Class(titanic)
#EDA using dtale
import dtale
dtale.show(titanic, ignore_duplicate=True)
import dtale
import pandas as pd
df = pd.DataFrame([dict(a=1, b=2, c=3)])
# Assigning a reference to a running D-Tale process
d = dtale.show(df)
# Accessing data associated with D-Tale process
tmp = d.data.copy()
tmp['d'] = 4
# Altering data associated with D-Tale process
# FYI: this will clear any front-end settings you have at the time for this process (filter, sorts, formatting)
d.data = tmp
# Shutting down D-Tale process
d.kill()
# using Python's `webbrowser` package it will try and open your server's default browser to this process
d.open_browser()
# There is also some helpful metadata about the process
d._data_id # the process's data identifier
d._url # the url to access the process
d2 = dtale.get_instance(
d._data_id
) # returns a new reference to the instance running at that data_id
dtale.instances() # prints a list of all ids & urls of running D-Tale sessions
def main():
"""We're going to create a beautiful app with Streamlit"""
menu = [
"Accueil", "Pandas Profile", "D-Tale", "Visualisation",
"Nuage de mots", "Machine Learning", "A propos"
]
selection = st.sidebar.selectbox("Fonctions", menu)
if selection == "Pandas Profile":
components.html(ha.alert_panda_prof(), height=190)
my_data = st.file_uploader("Charger le fichier CSV", type=['csv'])
if my_data is not None:
df = pd.read_csv(my_data)
st.dataframe(df.head(10))
eda_profil = ProfileReport(df,
title='Pandas Profiling Report...',
explorative=True)
st_profile_report(eda_profil)
elif selection == "D-Tale":
components.html(ha.alert_dtale(), height=190)
data_file = st.file_uploader("Charger le fichier CSV", type=['csv'])
if data_file is not None:
df = pd.read_csv(data_file)
st.dataframe(df.head())
d = dtale.show(df)
d.open_browser()
if st.button("Générer le rapport"):
report = sv.analyze(df)
report.show_html()
utils.st_display_sweetviz("SWEETVIZ_REPORT.html")
components.html(ha.alert_warning(), 1000)
elif selection == "Visualisation":
# Image d'entête
image = Image.open('dataviz.png')
col2, col1 = st.beta_columns([1, 3])
col2.image(
"https://idoc-projets.ias.u-psud.fr/redmine/attachments/download/121/sunburst.gif",
caption='',
width=None,
use_column_width=True)
col1.image(image, caption='', width=None, use_column_width=True)
# Visualisation catégorie / rating / reviews
cat1, cat2 = st.beta_columns(2)
datas = utils.lire_dataset(my_db_clean)
fig = px.histogram(datas,
x='Rating',
y='Category',
title='Somme des notes par catégorie',
color='Category')
cat1.plotly_chart(fig)
fig = px.histogram(datas,
x='Reviews',
y='Category',
title='Somme des commentaires par catégorie',
color='Category')
cat2.plotly_chart(fig)
# Visualisation sunburst / pie
perc1, perc2 = st.beta_columns(2)
fig = px.sunburst(datas,
path=['Type', 'Category', 'Genres'],
title='Types, Catégories et genres')
perc1.plotly_chart(fig)
fig = px.pie(datas,
names='Type',
title='Pourcentage apllication gratuites/Payantes',
color_discrete_sequence=px.colors.sequential.RdBu)
perc2.plotly_chart(fig)
# Visualisation histo
hist1, hist2 = st.beta_columns(2)
hist_data = [list(datas['Rating'])]
group_labels = ['Rating']
fig = ff.create_distplot(hist_data, group_labels)
hist1.plotly_chart(fig)
counts, bins = np.histogram(datas.Rating, bins=range(0, 6, 1))
bins = 0.5 * (bins[:-1] + bins[1:])
fig = px.bar(x=bins,
y=counts,
labels={
'x': 'Rating',
'y': 'Count'
},
title='Distribution des notes')
hist2.plotly_chart(fig)
elif selection == "Nuage de mots":
# General
img1, img2 = st.beta_columns(2)
img1.image('datas/wordcloud/general.png')
img2.image('datas/wordcloud/free_app.png')
# Free App
img3, img4 = st.beta_columns(2)
img3.image('datas/wordcloud/free_app_pos.png')
img4.image('datas/wordcloud/free_app_neg.png')
# Paid app
img5, img6 = st.beta_columns(2)
img5.image('datas/wordcloud/paid_app.png')
img6.image('datas/wordcloud/paid_app_pos.png')
img7, img8 = st.beta_columns(2)
img7.image('datas/wordcloud/paid_app_neg.png')
elif selection == "Machine Learning":
image = Image.open('machine learning.jpg')
col1, col2 = st.beta_columns([3, 1])
col2.image(
"https://static.wixstatic.com/media/bb7b70_d5fde322f7914060b7d997ba9d506a50~mv2.gif",
caption='',
width=None,
use_column_width=True)
col1.image(image, caption='', width=None, use_column_width=True)
if st.checkbox("Afficher le dataset"):
datas = utils.lire_dataset(my_db)
st.write(datas.head())
if st.checkbox("Afficher graph valeurs manquantes"):
col1, col2 = st.beta_columns([2, 1])
df = datas.isnull()
fig = px.imshow(df)
col1.plotly_chart(fig)
col2.write(datas.isnull().sum())
col2.write(
"On peut voir que la colonne **Rating** contient la plupart des valeurs manquantes. A sa suite on a **Current Ver**, **Adroid ver** et **Type**."
)
if st.checkbox("Afficher DB ok"):
datas = utils.lire_dataset(my_db_clean)
st.write(datas.head())
mat1, mat2 = st.beta_columns(2)
fig = px.scatter_matrix(
datas,
dimensions=["Rating", "Reviews", "Size", "Installs", "Price"],
color="Type",
symbol="Type",
title="Matrix de dispersion des variables continues")
fig.update_traces(diagonal_visible=False)
mat1.plotly_chart(fig)
fig = px.imshow(
datas[["Rating", "Reviews", "Size", "Installs",
"Price"]].corr(),
labels=dict(x="", y="", color="Corrélation"),
)
mat2.plotly_chart(fig)
if st.checkbox("Make model"):
#mon_score = utils.transform_var_model(my_db_clean)
mon_score = utils.make_model(my_db_clean)
st.success(mon_score)
elif selection == "A propos":
#st.subheader("Team presentation")
components.html(hp.pied_de_page(), height=800)
#components.iframe('http://www.ingemedia.net/',height=1000, scrolling=True)
else:
components.html(hp.entete_de_page(), height=1600)
