def get_model_div(key):
models = db.get('models')
model = models[key]
summary = model['summary']
tag = model['tag']
type = model['type']
params = model['params']
anova = model['anova']
x_col = model['x_col']
y_col = model['y_col']
error_mean = model['error_mean']
df_stats = common.get_stats_df(summary, x_col, y_col)
stats_div = dbc.Table.from_dataframe(df_stats,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
df_coeff = common.get_coeff_df(params, x_col)
coeff_div = dbc.Table.from_dataframe(df_coeff,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
anova_div = common.get_anova_div(anova)
div = html.Div([
html.H2("Model: " + key),
html.H2("Tag: Tag" + str(tag)),
html.H2("Type: " + type),
html.H2('Statistics Summary Table'), stats_div,
html.H2('Linear Regression Coefficients'), coeff_div,
html.H2('Error Mean = ' + str(round(error_mean, 4))),
html.Br(),
html.H2('Anova'), anova_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
def stats_table_and_linear_regression(json_ordered_data):
if json_ordered_data is None:
return (common.msg(None), generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "")
dff = pd.read_json(json_ordered_data, orient='split')
col = list(dff.columns)
y = list(dff[col[-1]])
data = []
x_col = col[:-1]
y_col = col[-1]
data = [[] for i in range(len(x_col))]
for i in range(len(x_col)):
x = dff[x_col[i]].values.tolist()
data[i] = x
##Team 3 API Integration
try:
model = LinearRegression()
db.put("lr.model", model)
db.put("lr.x_col", x_col)
db.put("lr.y_col", y_col)
(summary, params, ycap) = model.fit(data, y)
db.put("lr.summary", summary)
db.put("lr.params", params)
db.put("lr.ycap", ycap)
error_mean = model.model_stats()['mean']
db.put("lr.error_mean", error_mean)
except (Exception, ValueError) as e:
return (common.error_msg("Linear Regression API Error: " + str(e)),
generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "")
df_stats = common.get_stats_df(summary, x_col, y_col)
table1 = dbc.Table.from_dataframe(df_stats,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
df_coeff = common.get_coeff_df(params, x_col)
table2 = dbc.Table.from_dataframe(df_coeff,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
trace_1 = go.Scatter(x=list(range(len(y))),
y=ycap,
name='Y Predicted (ŷ)',
line=dict(width=2, color='rgb(229, 151, 50)'))
trace_2 = go.Scatter(x=list(range(len(y))),
y=y,
name='Y Actual',
line=dict(width=2, color='rgb(106, 181, 135)'))
ydiff = [y[i] - ycap[i] for i in range(len(y))]
trace_3 = go.Scatter(x=list(range(len(y))),
y=ydiff,
line=dict(width=2, color='rgb(236, 10, 15)'))
fig1 = go.Figure(data=[trace_1, trace_2], layout=y_ycap_title)
fig2 = go.Figure(data=[trace_3], layout=error_title)
error_mean = html.H2('Error Mean = ' +
str(round(db.get('lr.error_mean'), 4)))
##Team 5 API Integration
anova = get_anova(y, ycap, len(params))
db.put('lr.anova', anova)
anova_div = common.get_anova_div(anova)
return (
common.success_msg("Linear Regression API Exceuted Successfully!!"),
table1, table2, fig1, fig2, error_mean, anova_div)
def lr_save_model(n_clicks):
model_name = db.get('cl.model_name')
if model_name is None or model_name == '':
return ("", "")
file = db.get("lr.file")
model = db.get("lr.model")
params = db.get("lr.params")
anova = db.get("lr.anova")
error_mean = db.get('lr.error_mean')
summary = db.get("lr.summary")
x_col = db.get("lr.x_col")
y_col = db.get("lr.y_col")
m = {
'file': file,
'tag': db.get('tags')[file],
'type': 'linear',
'name': model_name,
'model': model,
'params': params,
'anova': anova,
'summary': summary,
'x_col': x_col,
'y_col': y_col,
'error_mean': error_mean
}
models = db.get('models')
if models is None:
models = {}
db.put('models', models)
models[model_name] = m
return (common.success_msg('Model "' + model_name +
'" Saved Successfully.'), "")
from dash.dependencies import Input, Output, State
import dash_table
import plotly.graph_objs as go
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'})
def hor_save_model(n_clicks):
model_name = db.get('hor.model_name')
if model_name is None or model_name == '':
return ("", "")
file = db.get("hor.file")
model = db.get("hor.model")
order = db.get("hor.order")
params = db.get("hor.params")
anova = db.get("hor.anova")
error_mean = db.get('hor.error_mean')
summary = db.get("hor.summary")
x_col = db.get("hor.x_col")
y_col = db.get("hor.y_col")
m = {
'file': file,
'tag': db.get('tags')[file],
'type': 'Higher Order Polynomial',
'name': model_name,
'model': model,
'order': order,
'params': params,
'no_of_coeff': len(params),
'anova': anova,
'summary': summary,
'x_col': x_col,
'y_col': y_col,
'error_mean': error_mean
}
models = db.get('models')
if models is None:
models = {}
db.put('models', models)
models[model_name] = m
return (common.success_msg('Model "' + model_name +
'" Saved Successfully.'), "")
def stats_table_and_hor_regression(json_ordered_data, hor_order):
if json_ordered_data is None or hor_order is None:
return (common.msg(None), generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "", "")
dff = pd.read_json(json_ordered_data, orient='split')
col = list(dff.columns)
x_col = [col[0]]
y_col = col[1]
dff = dff.sort_values(by=x_col)
x = list(dff[col[0]])
y = list(dff[col[1]])
##Team 4 API Integration
try:
db.put("hor.x_col", x_col)
db.put("hor.y_col", y_col)
(ycap, params) = Building_model_equation(x, y, hor_order)
print(params)
params = params.tolist()
print(params)
db.put("hor.params", params)
db.put("hor.ycap", ycap)
db.put("hor.order", hor_order)
error = 10.0
for i in range(len(y)):
error += y[i] - ycap[i]
error_mean = error / len(y)
db.put("hor.error_mean", error_mean)
db.put("hor.error_mean", error_mean)
## Team 3 API call for Summary Statistics
model = LinearRegression()
(summary, params_ignore, ycap_ignore) = model.fit([x], y)
db.put("hor.summary", summary)
except (Exception, ValueError) as e:
return (common.error_msg("Higher Order Regression API Error: " +
str(e)),
generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "", "")
df_stats = common.get_stats_df(summary, x_col, y_col)
table1 = dbc.Table.from_dataframe(df_stats,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
df_coeff = common.hor_get_coeff_df(params)
table2 = dbc.Table.from_dataframe(df_coeff,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
trace_actual = go.Scatter(x=x,
y=y,
name='Y Actual',
mode='markers',
marker=dict(color='rgb(106, 181, 135)'))
trace_predict = go.Scatter(x=x,
y=ycap,
name='Y Predicted (ŷ)',
line=dict(width=2, color='rgb(229, 151, 50)'))
ydiff = [y[i] - ycap[i] for i in range(len(y))]
trace_error = go.Scatter(x=x,
y=ydiff,
line=dict(width=2, color='rgb(236, 10, 15)'))
x_title = "x (" + str(x_col[0]) + ")"
y_title = "y,ŷ(" + str(y_col) + ")"
y_ycap_title = go.Layout(title='Actual vs Predicted Y Plot',
hovermode='closest',
xaxis={'title': x_title},
yaxis={'title': y_title})
error_title = go.Layout(title='Error Plot',
hovermode='closest',
xaxis={'title': x_title},
yaxis={'title': 'Error = y - ŷ'})
fig1 = go.Figure(data=[trace_predict, trace_actual], layout=y_ycap_title)
fig2 = go.Figure(data=[trace_error], layout=error_title)
error_mean = html.H2('Error Mean = ' +
str(round(db.get('hor.error_mean'), 4)))
##Team 5 API Integration
anova = get_anova(y, ycap, len(params))
db.put('hor.anova', anova)
anova_div = common.get_anova_div(anova)
independent_var = ','.join(x_col)
return (common.success_msg(
"Higher Order Regression API Exceuted Successfully!!"), table1, table2,
fig1, fig2, error_mean, anova_div, html.H2(independent_var))
import dash_table
import plotly.graph_objs as go
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.higher_order_regression.higher_order_polynomial_V1 import *
from dataanalytics.stats_linear_regression.linear_regression import LinearRegression
from dataanalytics.stat_anova.anova import get_anova
file = db.get('hor.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'})
def stats_table_and_linear_regression(json_ordered_data):
if json_ordered_data is None:
return (common.msg(None), generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "", "")
dff = pd.read_json(json_ordered_data, orient='split')
col = list(dff.columns)
x_col = col[:-1]
y_col = col[-1]
if len(x_col) == 1:
dff = dff.sort_values(by=x_col)
data = [[] for i in range(len(x_col))]
for i in range(len(x_col)):
x = dff[x_col[i]].values.tolist()
data[i] = x
y = list(dff[col[-1]])
##Team 3 API Integration
try:
model = LinearRegression()
db.put("lr.model", model)
db.put("lr.x_col", x_col)
db.put("lr.y_col", y_col)
(summary, params, ycap) = model.fit(data, y)
db.put("lr.summary", summary)
db.put("lr.params", params)
db.put("lr.ycap", ycap)
error_mean = model.model_stats()['mean']
db.put("lr.error_mean", error_mean)
except (Exception, ValueError) as e:
return (common.error_msg("Linear Regression API Error: " + str(e)),
generate_table(pd.DataFrame(columns=[])),
generate_table(pd.DataFrame(columns=[])), y_ycap_fig,
error_fig, "", "", "")
df_stats = common.get_stats_df(summary, x_col, y_col)
table1 = dbc.Table.from_dataframe(df_stats,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
df_coeff = common.get_coeff_df(params, x_col)
table2 = dbc.Table.from_dataframe(df_coeff,
striped=True,
bordered=True,
hover=True,
style=common.table_style)
if len(data) == 1:
trace_x = data[0]
x_title = "x (" + str(x_col[0]) + ")"
trace_actual = go.Scatter(x=trace_x,
y=y,
name='Y Actual',
mode='markers',
marker=dict(color='rgb(106, 181, 135)'))
else:
trace_x = list(range(len(y)))
x_title = 'Sequence of data points'
trace_actual = go.Scatter(x=trace_x,
y=y,
name='Y Actual',
line=dict(width=2,
color='rgb(106, 181, 135)'))
trace_predict = go.Scatter(x=trace_x,
y=ycap,
name='Y Predicted (ŷ)',
line=dict(width=2, color='rgb(229, 151, 50)'))
ydiff = [y[i] - ycap[i] for i in range(len(y))]
trace_error = go.Scatter(x=trace_x,
y=ydiff,
line=dict(width=2, color='rgb(236, 10, 15)'))
y_title = "y,ŷ(" + str(y_col) + ")"
y_ycap_title = go.Layout(title='Actual vs Predicted Y Plot',
hovermode='closest',
xaxis={'title': x_title},
yaxis={'title': y_title})
error_title = go.Layout(title='Error Plot',
hovermode='closest',
xaxis={'title': x_title},
yaxis={'title': 'Error = y - ŷ'})
fig1 = go.Figure(data=[trace_predict, trace_actual], layout=y_ycap_title)
fig2 = go.Figure(data=[trace_error], layout=error_title)
error_mean = html.H2('Error Mean = ' +
str(round(db.get('lr.error_mean'), 4)))
##Team 5 API Integration
anova = get_anova(y, ycap, len(params))
db.put('lr.anova', anova)
anova_div = common.get_anova_div(anova)
independent_var = ','.join(x_col)
return (
common.success_msg("Linear Regression API Exceuted Successfully!!"),
table1, table2, fig1, fig2, error_mean, anova_div,
html.H2(independent_var))