import sys
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
both_df = DfLoad.eng_both()
run_analyses([
{
'name': 'has_objc',
'df': both_df,
'index': 'eng_TAMsimp',
'columns': 'has_objc',
'examples': [],
},
{
'name': 'has_loca',
'df': both_df,
'index': 'eng_TAMsimp',
'columns': ['has_loca'],
'examples': [],
},
{
'name': 'has_time',
'df': both_df,
'index': 'eng_TAMsimp',
'columns': ['has_time'],
'examples': [],
import sys
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
eng_df = DfLoad.eng_agree()
# features needed for selections
main_genre = ['prose', 'poetry', 'prophetic']
main_dom = ['Q', 'N']
run_analyses([
{
'name': 'clause_type',
'df': eng_df,
'index': 'eng_TAM',
'columns': 'clause_type',
},
{
'name': 'clause_rela',
'df': eng_df,
'index': 'eng_TAM',
'columns': 'clause_rela',
},
{
'name': 'clause_rela',
'df': eng_df,
'index': 'eng_TAM',
import sys
import pandas as pd
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
agg_df = DfLoad.eng_simp_agree()
esv_df = DfLoad.esv()
niv_df = DfLoad.niv()
eng_df = DfLoad.eng_both()
disag_df_simp = DfLoad.eng_simp_disagree()
disag_df = DfLoad.eng_disagree()
def sum_top_values(df):
"""Sums the top values of dataframes."""
top = 0.015
pr_df = df / df.sum()
top_pr = pr_df.loc[pr_df['sum'] >= top]
top_ct = df.loc[top_pr.index]
top_sum = pd.DataFrame(top_ct.sum())
sum_pr = pd.DataFrame(top_pr.sum())
data = {
'top_ct': top_ct,
'top_pr': top_pr,
'top_sum': top_sum,
'top_sum_pr': sum_pr,
import sys
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
eng_df = DfLoad.eng_agree()
esv_df = DfLoad.esv()
niv_df = DfLoad.niv()
both_df = DfLoad.eng_both()
disag_df = DfLoad.eng_disagree()
run_analyses([
{
'name': 'eng_tenses',
'df': eng_df,
'index': 'eng_TAM',
},
{
'name': 'esv_tenses',
'df': esv_df,
'index': 'esv_TAM',
},
{
'name': 'niv_tenses',
'df': niv_df,
'index': 'niv_TAM',
},
{
import pandas as pd
from load_dfs import DfLoader
DfLoad = DfLoader(
'/Users/cody/github/CambridgeSemiticsLab/Gesenius_data/results/csv/qtl')
qatal_df = DfLoad.df_safe()
eng_df = DfLoad.eng_agree()
esv_df = DfLoad.esv()
niv_df = DfLoad.niv()
disag_df = DfLoad.eng_disagree()
print(disag_df.shape)
print(disag_df.head())
#test = pd.pivot_table(
# eng_df,
# index='eng_TAM',
# columns='has_objc',
# aggfunc='size',
# fill_value=0,
# #dropna=False,
#)
print(test)
import sys
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
esv_df = DfLoad.esv()
# features needed for selections
main_genre = ['prose', 'poetry', 'prophetic']
main_dom = ['Q', 'N']
run_analyses(
[
{
'name': 'clause_type',
'df': esv_df,
'index': 'esv_TAM',
'columns': 'clause_type',
},
{
'name': 'clause_rela',
'df': esv_df,
'index': 'esv_TAM',
'columns': 'clause_rela',
},
{
'name': 'cltype_simp',
'df': esv_df,
import sys
# NB snakemake runs script from /workflow directory
sys.path.append('scripts/analysis')
from load_dfs import DfLoader
from analysis import run_analyses
# load the dataframes
DfLoad = DfLoader(snakemake.input.data_dir)
niv_df = DfLoad.niv()
# features needed for selections
main_genre = ['prose', 'poetry', 'prophetic']
main_dom = ['Q', 'N']
run_analyses([
{
'name': 'clause_type',
'df': niv_df,
'index': 'niv_TAM',
'columns': 'clause_type',
},
{
'name': 'clause_rela',
'df': niv_df,
'index': 'niv_TAM',
'columns': 'clause_rela',
},
{
'name': 'cltype_simp',
'df': niv_df,