In [1]:

import pandas as pd
import forestplot as fp

Top of plot should not be getting cut off¶

See issue #47

In [2]:

df = pd.read_csv("../examples/data/regression1.csv")
df

Out[2]:

	varname	or	low	high
0	a	1.761471	0.926563	3.022285
1	b	1.443660	0.517059	3.130794
2	c	1.525227	0.603459	3.082003
3	d	0.895682	0.463703	1.660016
4	e	4.025670	1.196941	8.932753
5	f	1.086105	0.555171	2.045735

In [3]:

fp.forestplot(df,  # the dataframe with results data
    estimate='or',  # col containing estimated effect size 
    ll='low', hl='high',  # columns containing conf. int. lower and higher limits
    varlabel='varname',  # column containing variable label
    ylabel='Confidence interval',  # y-label title
    xlabel='Odds Ratio',  # x-label title
    color_alt_rows=True,
    figsize=(4,8),
    **{
        'xline' : 1.,
        "xlinestyle": (0, (10, 5)),  # long dash for x-reference line 
    }
)

Out[3]:

<Axes: xlabel='Odds Ratio', ylabel='Confidence interval'>

Capitalization of strings should be preserved¶

In [4]:

df = pd.read_csv("../examples/data/sleep.csv")
df

Out[4]:

	n	r	CI95%	p-val	BF10	power	var	hl	ll	moerror	group	label
0	706	0.090373	[0.02 0.16]	1.630887e-02	8.390000e-01	0.67	age	0.16	0.02	0.069627	age	in years
1	706	0.048081	[-0.03 0.12]	2.019484e-01	1.060000e-01	0.25	clerical	0.12	-0.03	0.071919	occupation	=1 if clerical worker
2	706	0.041229	[-0.03 0.11]	2.739475e-01	8.600000e-02	0.19	construc	0.11	-0.03	0.068771	occupation	=1 if construction worker
3	706	-0.095004	[-0.17 -0.02]	1.155151e-02	1.137000e+00	0.72	educ	-0.02	-0.17	0.075004	labor factors	years of schooling
4	706	-0.102825	[-0.18 -0.03]	6.246660e-03	1.967000e+00	0.78	gdhlth	-0.03	-0.18	0.072825	health factors	=1 if in good or excel. health
5	706	-0.066997	[-0.14 0.01]	7.524015e-02	2.290000e-01	0.43	smsa	0.01	-0.14	0.076997	area of residence	=1 if live in smsa
6	706	-0.035909	[-0.11 0.04]	3.407214e-01	7.400000e-02	0.16	male	0.04	-0.11	0.075909	other factors	=1 if male
7	706	0.027147	[-0.05 0.1 ]	4.714176e-01	6.100000e-02	0.11	prot	0.10	-0.05	0.072853	other factors	=1 if Protestant
8	706	0.001782	[-0.07 0.08]	9.623058e-01	4.700000e-02	0.05	selfe	0.08	-0.07	0.078218	labor factors	=1 if self employed
9	706	0.078600	[0. 0.15]	3.679946e-02	4.150000e-01	0.55	south	0.15	0.00	0.071400	area of residence	=1 if live in south
10	706	0.007881	[-0.07 0.08]	8.344125e-01	4.800000e-02	0.06	spsepay	0.08	-0.07	0.072119	other factors	spousal wage income
11	706	-0.321384	[-0.39 -0.25]	1.994095e-18	1.961000e+15	1.00	totwrk	-0.25	-0.39	0.071384	labor factors	mins worked per week
12	706	-0.013262	[-0.09 0.06]	7.250012e-01	5.000000e-02	0.06	yngkid	0.06	-0.09	0.073262	family factors	=1 if children < 3 present
13	706	0.063997	[-0.01 0.14]	8.928507e-02	1.990000e-01	0.40	yrsmarr	0.14	-0.01	0.076003	family factors	years married
14	532	-0.049450	[-0.13 0.04]	2.548774e-01	1.040000e-01	0.21	hrwage	0.04	-0.13	0.089450	labor factors	hourly wage

In [5]:

fp.forestplot(df,  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # columns containing conf. int. lower and higher limits
              varlabel="label",  # column containing variable label
              ylabel="Confidence interval",  # y-label title
              xlabel="Pearson correlation",  # x-label title
              )

Out[5]:

<Axes: xlabel='Pearson correlation', ylabel='Confidence interval'>

Kwargs for p-value thresholds and symbols should be respected¶

In [6]:

fp.forestplot(df,  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # columns containing conf. int. lower and higher limits
              varlabel="label",  # column containing variable label
              pval="p-val",  # Column of p-value to be reported on right
              decimal_precision=3,
              symbols=("$^a$", "$^b$", "$^c$"),
              thresholds=(0.001, 0.01, 0.05)
              )

Out[6]:

<Axes: >

CI label and P-value label should have same height fontsize¶

In [7]:

fp.forestplot(df,  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # columns containing conf. int. lower and higher limits
              varlabel="label",  # column containing variable label
              pval="p-val",  # Column of p-value to be reported on right
              ylabel="Confidence interval",  # ylabel to print
              )

Out[7]:

<Axes: ylabel='Confidence interval'>

> 6 rows should work¶

In [10]:

fp.forestplot(df,  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # lower & higher limits of conf. int.
              varlabel="label",  # column containing the varlabels to be printed on far left
              capitalize="capitalize",  # Capitalize labels
              pval="p-val",  # column containing p-values to be formatted
              annote=["n", "power", "est_ci"],  # columns to report on left of plot
              annoteheaders=["N", "Power", "Est. (95% Conf. Int.)"],  # ^corresponding headers
              rightannote=["formatted_pval", "group"],  # columns to report on right of plot 
              right_annoteheaders=["P-value", "Variable group"],  # ^corresponding headers
              xlabel="Pearson correlation coefficient",  # x-label title
              table=True,  # Format as a table
              )

Out[10]:

<Axes: xlabel='Pearson correlation coefficient'>

$\leq$ 6 rows should work¶

In [12]:

fp.forestplot(df.head(6),  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # lower & higher limits of conf. int.
              varlabel="label",  # column containing the varlabels to be printed on far left
              capitalize="capitalize",  # Capitalize labels
              pval="p-val",  # column containing p-values to be formatted
              annote=["n", "power", "est_ci"],  # columns to report on left of plot
              annoteheaders=["N", "Power", "Est. (95% Conf. Int.)"],  # ^corresponding headers
              rightannote=["formatted_pval", "group"],  # columns to report on right of plot 
              right_annoteheaders=["P-value", "Variable group"],  # ^corresponding headers
              xlabel="Pearson correlation coefficient",  # x-label title
              table=True,  # Format as a table
              )

Out[12]:

<Axes: xlabel='Pearson correlation coefficient'>

In [14]:

fp.forestplot(df.head(3),  # the dataframe with results data
              estimate="r",  # col containing estimated effect size 
              ll="ll", hl="hl",  # lower & higher limits of conf. int.
              varlabel="label",  # column containing the varlabels to be printed on far left
              capitalize="capitalize",  # Capitalize labels
              pval="p-val",  # column containing p-values to be formatted
              annote=["n", "power", "est_ci"],  # columns to report on left of plot
              annoteheaders=["N", "Power", "Est. (95% Conf. Int.)"],  # ^corresponding headers
              rightannote=["formatted_pval", "group"],  # columns to report on right of plot 
              right_annoteheaders=["P-value", "Variable group"],  # ^corresponding headers
              xlabel="Pearson correlation coefficient",  # x-label title
              table=True,  # Format as a table
              )

Out[14]:

<Axes: xlabel='Pearson correlation coefficient'>

In [ ]: