def display_data(value):
"""Displaying the head for the selected file."""
db_value = db.get("file")
if value is None and db_value is None:
return ""
elif value is None and not db_value is None:
value = db_value
format = FileUtils.file_format(value)
if format == 'csv' or format == 'txt':
path = FileUtils.path('raw', value)
head = DataUtils.read_text_head(path)
table_col = [
html.Col(style={'width': "10%"}),
html.Col(style={'width': "90%"})
]
table_header = [
html.Thead(html.Tr([html.Th("Row No"),
html.Th("Data")]))
]
rows = []
for i in range(len(head)):
row = html.Tr([html.Td(i + 1), html.Td(head[i])])
rows.append(row)
table_body = [html.Tbody(rows)]
table = dbc.Table(table_col + table_header + table_body,
bordered=True,
style=common.table_style)
div = [
common.msg("Selected File: " + value),
common.msg("Selected Format: " + format), table,
html.Br(), csv_properties_div
]
elif format == 'xls' or format == 'xlsx':
path = FileUtils.path('raw', value)
xls = pd.ExcelFile(path)
sheets = xls.sheet_names
div = [
common.msg("Selected File: " + value),
common.msg("Selected Format: " + format),
common.msg("Select Sheet:"),
html.Div([
dcc.Dropdown(id='xls-file-sheet',
options=[{
'label': sheet,
'value': sheet
} for sheet in sheets],
value=None,
multi=False)
],
style={
'margin': '10px',
'width': '50%'
}),
html.Div([], id="display-xls-file")
]
else:
div = "Format Not Supported!!"
db.put("file", value)
db.put("format", format)
return div
def xls_file_sheet(value):
file = db.get("file")
div = None
db_value = db.get("sheet")
if value is None and db_value is None:
div = []
elif value is None and not db_value is None:
value = db_value
if not value is None:
db.put('sheet', value)
path = FileUtils.path('raw', file)
xls = pd.ExcelFile(path)
df = pd.read_excel(xls, value)
table = html.Div([
dash_table.DataTable(
data=df.iloc[:10].to_dict('rows'),
columns=[{'name': i, 'id': i} for i in df.columns]
),
html.Hr(),
])
div = [html.Br(),
table,
html.Br(),
xls_properties_div]
return div
def apply_file_properties(n):
file = db.get("file")
format = db.get("format")
sep = db.get("file_separator")
header = db.get("file_header")
div = None
df = None
if format is None:
div = None
return div
elif (format == 'csv' or format == 'txt' or format == 'xls'
or format == 'xlsx') and header is None:
div = common.error_msg('Please Select Header!!')
return div
elif format == 'csv' or format == 'txt':
if sep is None:
sep = ','
db.put("file_separator", sep)
path = FileUtils.path('raw', file)
df = DataUtils.read_csv(path, sep, header)
msg = "Following Properties Applied. Separator=" + sep + " Header=" + str(
header)
elif format == 'xls' or format == 'xlsx':
path = FileUtils.path('raw', file)
sheet = db.get("sheet")
df = DataUtils.read_xls(path, sheet, header)
msg = "Following Properties Applied. Header=" + str(header)
table = dbc.Table.from_dataframe(df.head(10),
striped=True,
bordered=True,
hover=True,
style=common.table_style)
button = dbc.Button("Clean & Save", color="primary", id='clean-save-file')
div = [
common.msg(msg), table,
html.Div(
[button, html.Br(),
html.Div([], id="cleaned-saved-file")],
style={
'padding': '10px',
'textAlign': 'center'
})
]
db.put("raw_data", df)
return div
def clean_save_file(n):
## Team 2 API Integration
df = db.get("raw_data")
file = db.get("file")
sheet = db.get("sheet")
tags = db.get('tags')
div = None
if (not n is None) and (not df is None):
try:
df, cleaned_df, defective_df, stats = data_cleaning(df)
if not sheet is None:
file = FileUtils.append_file_name(file, sheet)
file = file.split('.')[0]
path = FileUtils.path('clean', file)
cleaned_df.to_csv(path, index=False)
### Tag the cleaned data ###
if file in tags:
tags[file] = tags[file] + 1
else:
tags[file] = 1
col_df = pd.DataFrame(columns=stats['col_name'])
col_df.loc[0] = stats['col_type']
stat_df = pd.DataFrame(columns=[
'Tag', 'Total no of Records', 'Cleaned no of Records',
'Defective no of Records'
])
stat_df.loc[0] = [
'Tag ' + str(tags[file]), stats['row_total'],
stats['row_cleaned'], stats['row_defect']
]
div = html.Div([
common.success_msg("File is Cleaned & Saved Successfully!!"),
html.H2('Cleaned Data Statistic'),
dbc.Table.from_dataframe(stat_df,
striped=True,
bordered=True,
hover=True,
style=common.table_style),
html.H2('Cleaned Data Schema'),
dbc.Table.from_dataframe(col_df,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
],
style={'margin': '10px'})
except Exception as e:
return common.error_msg("Data Cleansing API Error: " + str(e))
return div
def read(dir: str, filename: str):
format = FileUtils.file_format(filename)
path = FileUtils.path(dir, filename)
op = None
if format == 'csv' or format == 'txt':
with open(path) as myfile:
head = [next(myfile).strip() for x in range(N)]
op = head
elif format == 'jpeg' or format == 'jpg' or format == 'gif':
""
else:
op = "Format Not Supported!!"
return op
def xls_file_sheet(value):
file = db.get("file")
div = None
db_value = db.get("sheet")
if value is None and db_value is None:
div = []
elif value is None and not db_value is None:
value = db_value
if not value is None:
db.put('sheet', value)
path = FileUtils.path('raw', file)
xls = pd.ExcelFile(path)
df = pd.read_excel(xls, value)
table = html.Div([
dbc.Table.from_dataframe(df.head(10),
striped=True,
bordered=True,
hover=True,
style=common.table_style),
html.Hr(),
])
div = [html.Br(), table, html.Br(), xls_properties_div]
return div
def linear_regression(n):
global df_cleaned
file = db.get('lr.file')
if file is None:
file = 'empty'
path = FileUtils.path('clean', file)
df_cleaned = pd.read_csv(path)
tdf = df_cleaned.head(10).round(4)
div = [
html.Div(children=[
html.H2(children='Cleaned Data: ' + file),
html.H2(children='Tag: Tag ' + str(db.get('tags')[file])),
dbc.Table.from_dataframe(tdf,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
]),
html.Hr(),
html.H3(children='Variable Selection and Plotting'),
html.Div([
html.Div([
html.Div(id='ordered-df', style={'display': 'none'}),
html.Hr(),
html.Label('Select X-axis variable for scatter plot'),
dcc.Dropdown(id='x-var-plot',
options=[{
'label': i,
'value': i
} for i in df_cleaned.columns],
multi=False),
html.Label('Select Y-axis variable for scatter plot'),
dcc.Dropdown(id='y-var-plot',
options=[{
'label': i,
'value': i
} for i in df_cleaned.columns],
multi=False),
html.Br(),
html.H2('Perform Linear Regression'),
html.Label('Select X variable from Dropdown'),
dcc.Dropdown(id='x-var-selection',
options=[{
'label': i,
'value': i
} for i in df_cleaned.columns],
multi=True),
html.Label('Select Y variable from Dropdown'),
dcc.Dropdown(id='y-var-selection',
options=[{
'label': i,
'value': i
} for i in df_cleaned.columns],
multi=False),
],
style={
'width': '48%',
'display': 'inline-block'
}),
html.Div([
html.Label('Scatter Plot'),
dcc.Graph(id='scatter-plot'),
],
style={
'width': '48%',
'float': 'right',
'display': 'inline-block'
}),
]),
html.Hr(),
html.Div([
html.Div([], id='linear-regression-status'),
html.Br(),
html.H2('Statistics Summary Table'),
html.Table(id='stats_table'),
html.H2('Linear Regression Coefficients'),
html.Table(id='coeff_table'),
html.H2('Plot')
]),
html.Br(),
html.Div([
dcc.Graph(id='lr-y-ycap-plot', figure=y_ycap_fig),
dcc.Graph(id='lr-error-plot', figure=error_fig),
html.Div([], id='lr-error-mean')
]),
html.Div([
html.Hr(),
html.H2('ANOVA Table'),
html.Div([], id='lr-anova-table'),
]),
html.Div([
html.Hr(),
dbc.Label(
'Predict Data (pass comma separated) Dependent Variables'),
dbc.Input(id="lr-predict-data",
placeholder="Model Name",
type="text"),
html.Br(),
dbc.Button("Predict", color="primary", id='lr-predict'),
html.Div([], id='lr-predict-display'),
html.Div([], id='lr-predict-data-do-nothing'),
]),
html.Div([
html.Hr(),
dbc.Label('Save Model'),
dbc.Input(id="lr-save-model",
placeholder="Model Name",
type="text"),
html.Br(),
dbc.Button("Save", color="primary", id='lr-save'),
html.Div([], id='lr-save-display'),
html.Div([], id='lr-save-model-do-nothing'),
])
]
return div
import pandas as pd
from dataanalytics.ux.app import app
from dataanalytics.ux.apps import common
from dataanalytics.ux.apps.common import *
from dataanalytics.framework.database import db
from dataanalytics.framework.file_utils import FileUtils
from dataanalytics.framework.data_utils import DataUtils
from dataanalytics.stats_linear_regression.linear_regression import LinearRegression
from dataanalytics.stat_anova.anova import get_anova
file = db.get('lr.file')
if file is None:
file = 'empty'
path = FileUtils.path('clean', file)
df_cleaned = pd.read_csv(path)
y_ycap_title = go.Layout(title='Actual vs Predicted Y Plot',
hovermode='closest',
xaxis={'title': 'Sequence of data points'},
yaxis={'title': 'y,ŷ'})
y_ycap_fig = go.Figure(data=[], layout=y_ycap_title)
error_title = go.Layout(title='Error Plot',
hovermode='closest',
xaxis={'title': 'Sequence of data points'},
yaxis={'title': 'Error = y - ŷ'})
error_fig = go.Figure(data=[], layout=error_title)
layout = html.Div(children=[