def salary_v_rating_scatter(df_chart, legend, separate=False):
"""
Description: Create an altair chart for a salary vs rating scatterplot.
:param df_chart: Dataframe of job listings with both salaries and ratings that will be used to make chart object
:type df_chart: pandas.DataFrame
:param legend: How we want plot to be organized i.e. by industry
:type legend: str in cols
:author: Jake Kim
"""
cols = [
'Job_title', 'Company', 'State', 'City', 'Min_Salary', 'Max_Salary',
'Job_Desc', 'Industry', 'Rating', 'Date_Posted', 'Valid_until',
'Job_Type'
]
assert isinstance(df_chart, pd.DataFrame)
assert legend in cols
avg_sal = list()
for i in range(df_chart.shape[0]):
assert df_chart.loc[i, 'Max_Salary'] > 0
assert df_chart.loc[i, 'Min_Salary'] > 0
avg_sal.append(
(df_chart.loc[i, 'Max_Salary'] + df_chart.loc[i, 'Min_Salary']) /
2)
df_chart['Avg_Salary'] = avg_sal
df_chart = Chart(df_chart)
if separate:
chart = df_chart.mark_point().encode(
x=alt.X('Avg_Salary', title='Avg Salary (USD)'),
y='Rating',
column=legend,
color=alt.Color(legend, scale=alt.Scale(scheme='dark2')))
else:
chart = df_chart.mark_point().encode(x=alt.X('Avg_Salary',
title='Avg Salary (USD)'),
y='Rating',
color=legend)
chart = chart.properties(title='Salary vs. Company Ratings',
height=700,
width=900)
chart = chart.configure_header(titleFontSize=18, labelFontSize=18)
chart = chart.configure_axis(titleFontSize=18,
labelFontSize=18,
tickCount=10)
chart = chart.configure_title(fontSize=18)
chart = chart.configure_point(size=75)
chart = chart.configure_legend(titleFontSize=18, labelFontSize=16)
return chart
def _plot_with_data_bar(source: alt.Chart,
line: alt.Chart,
type_: ValueType,
width: Optional[int] = None,
height: Optional[int] = None) -> alt.Chart:
width = 800 if width is None else width
height = 400 if height is None else height
# TODO: Add validation that the x and y series names are correct
# Create a selection that chooses the nearest point & selects based on x-value
nearest = alt.selection(type='single', nearest=True, on='mouseover', fields=['days'],
empty='none')
# Transparent selectors across the chart. This is what tells us
# the x-value of the cursor
selectors = alt.Chart(source).mark_point().encode(
x='days:Q',
opacity=alt.value(0),
).add_selection(
nearest
)
# Draw points on the line, and highlight based on selection
points = line.mark_point().encode(
opacity=alt.condition(nearest, alt.value(1), alt.value(0))
)
# Draw text labels near the points, and highlight based on selection
text = line.mark_text(align='left', dx=5, dy=10).encode(
text=alt.condition(nearest, f'{type_.value}:Q', alt.value(' '), format=".0f")
)
# Draw a rule at the location of the selection
rules = alt.Chart(source).mark_rule(color='gray').encode(
x='days:Q',
).transform_filter(
nearest
)
# Put the five layers into a chart and bind the data
chart = alt.layer(
line, selectors, points, rules, text
).properties(
width=width, height=height
)
return chart
def plot_capita_map(CA_data,path):
alt.renderers.enable('default')
countyinfo=pd.read_csv('data/CA_County_Pop_Miles.csv')
countyinfo=pd.read_csv('data/CA_County_Pop_Miles.csv', index_col=0)
county_count=pd.DataFrame(CA_data.groupby('County')['ID'].count())
#print(county_count)
countyinfo['Count']=county_count['ID']
#print(countyinfo)
countyinfo['County']=countyinfo.index
countyinfo['Accidents_Per_Capita']=countyinfo['Count']/countyinfo['pop2020']
countyinfo['Accidents_Per_Square_Mile']=countyinfo['Count']/countyinfo['Square_Miles']
countyinfo['Pop_Density']=countyinfo['pop2020']/countyinfo['Square_Miles']
newdf=countyinfo[['Pop_Density','Accidents_Per_Square_Mile']]
corrMatrix = newdf.corr()
sns.heatmap(corrMatrix, annot=True,annot_kws={"size":20})
plt.show()
countyinfo['Pop_Density']=countyinfo['pop2020']/countyinfo['Square_Miles']
chart=Chart(countyinfo)
chart.mark_point().encode(y=alt.X('Accidents_Per_Square_Mile',axis=alt.Axis(title='Accidents Per Square Mile')),
x=alt.Y('Pop_Density',axis=alt.Axis(title='Population Density'))).properties(
title='Accidents Per Sq Mile vs Population Density').interactive()
plt.show()
newdf=countyinfo[['Pop_Density','Accidents_Per_Capita']]
corrMatrix = newdf.corr()
sns.heatmap(corrMatrix, annot=True, annot_kws={"size":20})
plt.show()
countyinfo['Pop_Density']=countyinfo['pop2020']/countyinfo['Square_Miles']
chart=Chart(countyinfo)
chart.mark_point().encode(y=alt.X('Accidents_Per_Capita',axis=alt.Axis(title='Accidents_Per_Capita')),
x=alt.Y('Pop_Density',scale=alt.Scale(type='log'),axis=alt.Axis(title='Population Density (log(x))'))).properties(
title='Accidents Per Capita vs Population Density').interactive()
plt.show()
def salary_v_listings_scatter(df_chart, legend, separate=False):
"""
Description: Create an altair chart for a salary vs job listings scatterplot
:param df_chart: Dataframe of job listings with both salaries and listings that will be used to make chart object
:type df_chart: pandas.DataFrame
:param legend: How we want plot to be organized i.e. by industry
:type legend: str in cols
:author: Jake Kim
"""
cols = [
'Job_title', 'Company', 'State', 'City', 'Min_Salary', 'Max_Salary',
'Job_Desc', 'Industry', 'Rating', 'Date_Posted', 'Valid_until',
'Job_Type'
]
assert legend in cols
assert isinstance(df_chart, pd.DataFrame)
listings = list(df_chart[legend])
listing_set = set(listings)
list_dict = dict.fromkeys(listing_set, 0)
for i in range(len(listings)):
list_dict[listings[i]] += 1
entries = list()
for i in range(df_chart.shape[0]):
entries.append(list_dict[df_chart.loc[i, legend]])
df_chart['Listings'] = entries
avg_sal = list()
for i in range(df_chart.shape[0]):
assert df_chart.loc[i, 'Max_Salary'] > 0
assert df_chart.loc[i, 'Min_Salary'] > 0
avg_sal.append(
(df_chart.loc[i, 'Max_Salary'] + df_chart.loc[i, 'Min_Salary']) /
2)
df_chart['Avg_Salary'] = avg_sal
df_chart = Chart(df_chart)
if separate:
chart = df_chart.mark_point().encode(x='Listings',
y=alt.Y('Avg_Salary',
title='Avg Salary (USD)'),
color=legend,
column=legend)
else:
chart = df_chart.mark_point().encode(x='Listings',
y=alt.Y('Avg_Salary',
title='Avg Salary (USD)'),
color=legend)
chart = chart.properties(title='Salary vs. # of Job Lstings',
height=700,
width=900)
chart = chart.configure_header(titleFontSize=14, labelFontSize=14)
chart = chart.configure_axis(titleFontSize=14,
labelFontSize=14,
tickCount=10)
chart = chart.configure_title(fontSize=14)
chart = chart.configure_legend(titleFontSize=14, labelFontSize=12)
chart = chart.configure_point(size=75)
return chart
prices_predict = compute_all_y(array, coefficients)
MSE2 = compute_mse(prices_actual, prices_predict)
if MSE2 > MSE1:
coefficients[1] = coefficients[1] - 0.02
prices_predict = compute_all_y(array, coefficients)
MSE3 = compute_mse(prices_actual, prices_predict)
if MSE3 < MSE1:
MSE1 = MSE3
else:
MSE1 = MSE2
coefficients[2] = coefficients[2] + 0.01
prices_predict = compute_all_y(array, coefficients)
MSE2 = compute_mse(prices_actual, prices_predict)
if MSE2 > MSE1:
coefficients[2] = coefficients[2] - 0.02
prices_predict = compute_all_y(array, coefficients)
MSE3 = compute_mse(prices_actual, prices_predict)
if MSE3 < MSE1:
MSE1 = MSE3
else:
MSE1 = MSE2
MSE_list.append(MSE1)
count += 1
attempt.append(count)
data = Data(attempt=attempt, MSE_list=MSE_list)
chart = Chart(data)
mark = chart.mark_point()
enc = mark.encode(x='attempt:Q', y='MSE_list:Q', )
enc.display()
