#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
import forestplot as fp


# ## Top of plot should not be getting cut off
# See issue [#47](https://github.com/LSYS/forestplot/issues/47)

# In[2]:


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


# 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 
    }
)


# ## Capitalization of strings should be preserved

# In[4]:


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


# 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
              )


# ## 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)
              )


# ## 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
              )


# ## > 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
              )


# ## $\leq$ 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
              )


# 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
              )


# In[ ]:





# In[ ]: