对job进行可视化分析

job_counts = df['job'].value_counts() job_counts_dict = dict(job_counts) job_counts_list = sorted(job_counts_dict.items(), key=lambda x:x[1], reverse=True) job_counts_df = pd.DataFrame(job_counts_list, columns=['job', 'count'])

TOOLS = "hover,save,pan,box_zoom,reset,wheel_zoom"

p = figure(x_range=job_counts_df['job'], plot_width=800, plot_height=400, tools=TOOLS, title="Job Counts") p.vbar(x='job', top='count', width=0.9, source=job_counts_df, line_color='white')

p.xgrid.grid_line_color = None p.y_range.start = 0 p.xaxis.major_label_orientation = 1.2 p.hover.tooltips = [("Count", "@count")]

output_file("job_counts.html") show(p)

对age进行可视化分析

age_counts = df['age'].value_counts() age_counts_dict = dict(age_counts) age_counts_list = sorted(age_counts_dict.items(), key=lambda x:x[0]) age_counts_df = pd.DataFrame(age_counts_list, columns=['age', 'count'])

TOOLS = "hover,save,pan,box_zoom,reset,wheel_zoom"

p = figure(plot_width=800, plot_height=400, tools=TOOLS, title="Age Counts") p.vbar(x='age', top='count', width=0.9, source=age_counts_df, line_color='white')

p.xgrid.grid_line_color = None p.y_range.start = 0 p.xaxis.major_label_orientation = 1.2 p.hover.tooltips = [("Count", "@count")]

output_file("age_counts.html") show(p