def raw_mr_apa_table_word(mod_raw_data_df, output_df):
mod_output_df = output_df[[
"Variable", "B", "95% CI B", "beta", "t", "adjusted_pvalues"
]]
pd.options.mode.chained_assignment = None
mod_output_df[["B", "beta", "t"]] = mod_output_df[[
"B", "beta", "t"
]].applymap(lambda x: "{:.2f}".format(x))
mod_output_df["adjusted_pvalues"] = mod_output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
mod_output_df.rename(columns={
"95% CI B": "95% CI",
"adjusted_pvalues": "p"
},
inplace=True)
mod_output_df.loc[
0,
"beta"] = "" # removes the beta value for constant as it is always 0
doc = Document()
table_rows_len = len(mod_output_df) + 1
table_cols_len = len(mod_output_df.columns)
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
for ind, var in enumerate(mod_output_df.columns):
table.cell(row_idx=0, col_idx=ind).text = var
for row in range(1, table_rows_len):
for col in range(0, table_cols_len):
table.cell(row_idx=row,
col_idx=col).text = mod_output_df.iloc[row - 1, col]
for cell in table.rows[0].cells:
helper_funcs.word_style(cell, italic=True)
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell,
top=global_vars.border_APA_word,
bottom=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
doc = helper_funcs.set_autofit(doc)
doc.add_paragraph("R squared adjusted = {R}".format(
R="{:.2f}".format(output_df["R2adj"][0])))
doc.add_paragraph(
"Dependent Variable: {DV}".format(DV=global_vars.raw_mr_outcomevar))
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def raw_mr_apa_table_excel(mod_raw_data_df, output_df):
mod_output_df = output_df[[
"Variable", "B", "95% CI B", "beta", "t", "adjusted_pvalues"
]]
pd.options.mode.chained_assignment = None
mod_output_df[["B", "beta", "t"]] = mod_output_df[[
"B", "beta", "t"
]].applymap(lambda x: "{:.2f}".format(x))
mod_output_df["adjusted_pvalues"] = mod_output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
mod_output_df.rename(columns={
"95% CI B": "95% CI",
"adjusted_pvalues": "p"
},
inplace=True)
mod_output_df.loc[
0,
"beta"] = "" # removes the beta value for constant as it is always 0
wb = Workbook()
ws = wb.active
ws.append(list(mod_output_df.columns))
for row in dataframe_to_rows(mod_output_df, index=False, header=False):
ws.append(row)
for cell in ws[1]:
cell.font = global_vars.font_header
for cell in ws[1] + ws[len(mod_output_df) + 1]:
cell.border = Border(top=global_vars.border_APA,
bottom=global_vars.border_APA)
for cell in ws[len(mod_output_df) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
for row in range(1, len(mod_output_df) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
table_notes = [
"R squared adjusted = {R}".format(
R="{:.2f}".format(output_df["R2adj"][0])),
"Dependent Variable: {DV}".format(DV=global_vars.raw_mr_outcomevar)
]
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def spss_mr_apa_table_word(mod_raw_data_df, output_df):
output_df.drop(columns=["pvalues"], inplace=True)
pd.options.mode.chained_assignment = None
output_df["adjusted_pvalues"] = output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
output_df.rename(columns={"adjusted_pvalues": "p"}, inplace=True)
doc = Document()
table_rows_len = len(output_df) + 1
table_cols_len = len(output_df.columns)
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
for ind, var in enumerate(output_df.columns):
table.cell(row_idx=0, col_idx=ind).text = var
for row in range(1, table_rows_len):
for col in range(0, table_cols_len):
table.cell(row_idx=row, col_idx=col).text = output_df.iloc[row - 1,
col]
for cell in table.rows[0].cells:
helper_funcs.word_style(cell, italic=True)
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell,
top=global_vars.border_APA_word,
bottom=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
doc = helper_funcs.set_autofit(doc)
DV_cell = mod_raw_data_df[mod_raw_data_df.columns[0]][
len(mod_raw_data_df[mod_raw_data_df.columns[0]]) - 1]
DV = DV_cell[DV_cell.find(":") + 2:]
doc.add_paragraph("R squared adjusted = X.XX")
doc.add_paragraph("Dependent Variable: {}".format(DV))
if output_df["95% CI"][0] == "[,]":
doc.add_paragraph(
"Confidence intervals were not found in the SPSS table. Please add them to your SPSS table and re-run the program or add them manually."
)
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def spss_mr_apa_table_excel(mod_raw_data_df, output_df):
output_df.drop(columns=["pvalues"], inplace=True)
pd.options.mode.chained_assignment = None
output_df["adjusted_pvalues"] = output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
output_df.rename(columns={"adjusted_pvalues": "p"}, inplace=True)
wb = Workbook()
ws = wb.active
for row in dataframe_to_rows(output_df, index=False, header=True):
ws.append(row)
for cell in ws[1]:
cell.font = global_vars.font_header
for row in range(1, len(output_df) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1]:
cell.border = Border(bottom=global_vars.border_APA,
top=global_vars.border_APA)
for cell in ws[len(output_df) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
DV_cell = mod_raw_data_df[mod_raw_data_df.columns[0]][
len(mod_raw_data_df[mod_raw_data_df.columns[0]]) - 1]
DV = DV_cell[DV_cell.find(":") + 2:]
table_notes = [
"R squared adjusted = X.XX", "Dependent variable: {}".format(DV)
]
if output_df["95% CI"][0] == "[,]":
table_notes.append(
"Confidence intervals were not found in the SPSS table. Please add them to your SPSS table and re-run the program or add them manually."
)
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def raw_pairttest_apa_table_excel(mod_raw_data_df, output_df):
output_df.drop(columns=["pvalues"], inplace=True)
apa_table_df = output_df[[
"Variable", "Time1_Mean", "Time1_SD", "Time2_Mean", "Time2_SD",
"Degrees of Freedom", "t", global_vars.effect_size_choice,
"adjusted_pvalues"
]]
pd.options.mode.chained_assignment = None
apa_table_df[list(apa_table_df.columns)[1:-1]] = apa_table_df[list(
apa_table_df.columns)[1:-1]].applymap(lambda x: "{:.2f}".format(x))
apa_table_df["adjusted_pvalues"] = apa_table_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
wb = Workbook()
ws = wb.active
ws.cell(row=1, column=1).value = "Variable"
ws.merge_cells("A1:A2")
ws.cell(row=1, column=1).font = global_vars.font_header
ws.cell(row=1, column=2).value = "Time 1"
ws.merge_cells("B1:C1")
ws.cell(row=1, column=4).value = "Time 2"
ws.merge_cells("D1:E1")
ws.cell(row=1, column=6).value = "df"
ws.merge_cells("F1:F2")
ws.cell(row=1, column=6).font = global_vars.font_header
ws.cell(row=1, column=7).value = "t"
ws.merge_cells("G1:G2")
ws.cell(row=1, column=7).font = global_vars.font_header
ws.cell(row=1, column=8).value = global_vars.effect_size_choice
ws.merge_cells("H1:H2")
ws.cell(row=1, column=8).font = global_vars.font_header
ws.cell(row=1, column=9).value = "p"
ws.merge_cells("I1:I2")
ws.cell(row=1, column=9).font = global_vars.font_header
for col in range(2, 5, 2):
ws.cell(row=2, column=col).value = "M"
ws.cell(row=2, column=col).font = global_vars.font_header
ws.cell(row=2, column=col + 1).value = "SD"
ws.cell(row=2, column=col + 1).font = global_vars.font_header
for row in dataframe_to_rows(apa_table_df, index=False, header=False):
ws.append(row)
for row in range(1, len(apa_table_df) + 3):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[2] + ws[len(apa_table_df) + 2]:
cell.border = Border(bottom=global_vars.border_APA)
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA)
if global_vars.effect_size_choice == "None":
ws.delete_cols(8)
helper_funcs.add_table_notes(ws, [])
helper_funcs.savefile(wb=wb)
def raw_pairttest_apa_table_word(mod_raw_data_df, output_df):
output_df.drop(columns=["pvalues"], inplace=True)
apa_table_df = output_df[[
"Variable", "Time1_Mean", "Time1_SD", "Time2_Mean", "Time2_SD",
"Degrees of Freedom", "t", global_vars.effect_size_choice,
"adjusted_pvalues"
]]
pd.options.mode.chained_assignment = None
apa_table_df[list(apa_table_df.columns)[1:-1]] = apa_table_df[list(
apa_table_df.columns)[1:-1]].applymap(lambda x: "{:.2f}".format(x))
apa_table_df["adjusted_pvalues"] = apa_table_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
doc = Document()
table_rows_len = len(apa_table_df) + 2
table_cols_len = len(apa_table_df.columns)
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
table.cell(row_idx=0, col_idx=0).text = "Variable"
table.cell(row_idx=0, col_idx=0).merge(table.cell(row_idx=1, col_idx=0))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=0), italic=True)
table.cell(row_idx=0, col_idx=1).text = "Time 1"
table.cell(row_idx=0, col_idx=1).merge(table.cell(row_idx=0, col_idx=2))
table.cell(row_idx=0, col_idx=3).text = "Time 2"
table.cell(row_idx=0, col_idx=3).merge(table.cell(row_idx=0, col_idx=4))
table.cell(row_idx=0, col_idx=5).text = "df"
table.cell(row_idx=0, col_idx=5).merge(table.cell(row_idx=1, col_idx=5))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=5), italic=True)
table.cell(row_idx=0, col_idx=6).text = "t"
table.cell(row_idx=0, col_idx=6).merge(table.cell(row_idx=1, col_idx=6))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=6), italic=True)
table.cell(row_idx=0, col_idx=7).text = global_vars.effect_size_choice
if global_vars.effect_size_choice != "None": # otherwise cant remove with delete columns below if merged; see helper_funcs.delete_columns_word func notes
table.cell(row_idx=0, col_idx=7).merge(table.cell(row_idx=1,
col_idx=7))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=7), italic=True)
table.cell(row_idx=0, col_idx=8).text = "p"
table.cell(row_idx=0, col_idx=8).merge(table.cell(row_idx=1, col_idx=8))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=8), italic=True)
for col in range(1, 4, 2):
table.cell(row_idx=1, col_idx=col).text = "M"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col),
italic=True)
table.cell(row_idx=1, col_idx=col + 1).text = "SD"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col + 1),
italic=True)
for row in range(2, table_rows_len):
for col in range(0, table_cols_len):
table.cell(row_idx=row,
col_idx=col).text = apa_table_df.iloc[row - 2, col]
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[2].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
if global_vars.effect_size_choice == "None":
helper_funcs.delete_columns_word(table, [7])
doc = helper_funcs.set_autofit(doc)
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def spss_corr_apa_table_excel(mod_raw_data_df, output_df):
# could very easily use the summ_corr_apa_table function here as I pass identical data - seperate is preferred, however, as might be updated/adjusted in the future
correlation_label = mod_raw_data_df.iloc[0, 1]
variables_list = list(mod_raw_data_df.columns)[2:]
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols, header_rows = variables_list, variables_list
wb = Workbook()
ws = wb.active
ws.append([""] + header_cols)
for ind, var in enumerate(header_rows):
ws.cell(row=ind + 2, column=1).value = var
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_rows) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
outside_loop_var = ws.cell(row=outside_loop_ind, column=1).value
elif global_vars.corr_table_triangle == "Lower triangle":
outside_loop_var = ws.cell(row=1, column=outside_loop_ind).value
for inside_loop_ind in range(inside_loop_ind_start,
len(header_cols) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
inside_loop_var = ws.cell(row=1, column=inside_loop_ind).value
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_var = ws.cell(row=inside_loop_ind, column=1).value
if outside_loop_var == inside_loop_var:
ws.cell(row=outside_loop_ind, column=inside_loop_ind).value = 1
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["var1"] == outside_loop_var) &
(output_df["var2"] == inside_loop_var)) | (
(output_df["var1"] == inside_loop_var) &
(output_df["var2"] == outside_loop_var))].iloc[0]
r = df_filtered[correlation_label]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
ws.cell(row=outside_loop_ind,
column=inside_loop_ind).value = r
elif global_vars.corr_table_triangle == "Lower triangle":
ws.cell(row=inside_loop_ind,
column=outside_loop_ind).value = r
if global_vars.corr_table_triangle != "Both":
inside_loop_ind_start += 1
for row in range(1, len(header_rows) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1]:
cell.font = global_vars.font_header
for row in range(2, len(header_rows) + 2):
ws.cell(row=row, column=1).font = global_vars.font_header
for cell in ws[len(header_rows) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA,
bottom=global_vars.border_APA)
table_notes = ["**p < 0.01", "*p < {}".format(global_vars.alpha_threshold)]
table_notes.append(
"Correlation Coefficient used: {}".format(correlation_label))
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def spss_corr_apa_table_word(mod_raw_data_df, output_df):
# could very easily use the summ_corr_apa_table function here as I pass identical data - seperate is preferred, however, as might be updated/adjusted in the future
correlation_label = mod_raw_data_df.iloc[0, 1]
variables_list = list(mod_raw_data_df.columns)[2:]
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols = [
x for x in variables_list
] # not straight up variables_list; pass by value vs pass by reference
header_rows = [x for x in variables_list]
# this adds an empty column where the significance signs will be placed for better presentation
# the code looks slightly wrong as it return a None array but it works
[header_cols.insert(x, "") for x in range(1, len(header_cols) * 2, 2)]
doc = Document()
table_rows_len = len(header_rows) + 1
table_cols_len = len(header_cols) + 1
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
for ind, var in enumerate([""] + header_cols):
table.cell(row_idx=0, col_idx=ind).text = var
for ind, var in enumerate([""] + header_rows):
table.cell(row_idx=ind, col_idx=0).text = var
if global_vars.corr_table_triangle == "Upper triangle":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_rows_len):
outside_loop_var = table.cell(row_idx=outside_loop_ind,
col_idx=0).text
for inside_loop_ind in range(inside_loop_ind_start,
table_cols_len):
inside_loop_var = table.cell(row_idx=0,
col_idx=inside_loop_ind).text
if inside_loop_var == "" or outside_loop_var == "": # this allows to skip the columns designed for the significance signs
continue
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["var1"] == outside_loop_var) &
(output_df["var2"] == inside_loop_var)) | (
(output_df["var1"] == inside_loop_var) &
(output_df["var2"] == outside_loop_var))].iloc[0]
r = df_filtered[correlation_label]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=outside_loop_ind,
col_idx=inside_loop_ind).text = r
table.cell(row_idx=outside_loop_ind,
col_idx=inside_loop_ind + 1).text = sign
inside_loop_ind_start += 2
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_cols_len):
outside_loop_var = table.cell(row_idx=0,
col_idx=outside_loop_ind).text
if outside_loop_var == "":
continue
else:
for inside_loop_ind in range(inside_loop_ind_start,
table_rows_len):
inside_loop_var = table.cell(row_idx=inside_loop_ind,
col_idx=0).text
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["var1"] == outside_loop_var) &
(output_df["var2"] == inside_loop_var)) | (
(output_df["var1"] == inside_loop_var) &
(output_df["var2"] == outside_loop_var))].iloc[0]
r = df_filtered[correlation_label]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = r
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind + 1).text = sign
inside_loop_ind_start += 1
elif global_vars.corr_table_triangle == "Both":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_cols_len):
outside_loop_var = table.cell(row_idx=0,
col_idx=outside_loop_ind).text
if outside_loop_var == "":
continue
else:
for inside_loop_ind in range(inside_loop_ind_start,
table_rows_len):
inside_loop_var = table.cell(row_idx=inside_loop_ind,
col_idx=0).text
if inside_loop_var == "": # this allows to skip the columns designed for the significance signs
continue
else:
if outside_loop_var == inside_loop_var:
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = "1"
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["var1"] == outside_loop_var) &
(output_df["var2"] == inside_loop_var)) | (
(output_df["var1"] == inside_loop_var) &
(output_df["var2"] == outside_loop_var)
)].iloc[0]
r = df_filtered[correlation_label]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = r
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind +
1).text = sign
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell,
top=global_vars.border_APA_word,
bottom=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
for cell in table.rows[0].cells:
helper_funcs.word_style(cell, italic=True)
for cell in table.columns[0].cells:
helper_funcs.word_style(cell, italic=True)
for i in range(1, table_cols_len, 2):
table.cell(row_idx=0,
col_idx=i).merge(table.cell(row_idx=0, col_idx=i + 1))
table.cell(row_idx=0, col_idx=i).text = table.cell(
row_idx=0, col_idx=i
).text[:
-1] # meging cells adds a paragraph break at the end; this gets rid of it
for cell in table.rows[0].cells:
helper_funcs.word_style(cell, italic=True)
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for cell in table.columns[0].cells:
helper_funcs.word_style(cell, italic=True)
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].paragraph_format.space_after = Inches(0)
cell.paragraphs[0].paragraph_format.space_before = Inches(0)
cell.paragraphs[0].paragraph_format.line_spacing = 1
for row in range(1, table_rows_len):
for col in range(1, table_cols_len, 2):
table.cell(
row_idx=row, col_idx=col
).paragraphs[0].paragraph_format.right_indent = Inches(-0.08)
table.cell(
row_idx=row, col_idx=col +
1).paragraphs[0].paragraph_format.left_indent = Inches(-0.06)
table.cell(
row_idx=row,
col_idx=col).paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.RIGHT
table.cell(row_idx=row, col_idx=col +
1).paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.LEFT
doc = helper_funcs.set_autofit(doc)
para = doc.add_paragraph("** ")
para.add_run("p").italic = True
para.add_run(" < 0.01")
para.add_run().add_break()
para.add_run("* ")
para.add_run("p").italic = True
para.add_run(" < {}".format(global_vars.alpha_threshold))
doc.add_paragraph(
"Correlation Coefficient used: {}".format(correlation_label))
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def raw_corr_apa_table_noCIs_excel(mod_raw_data_df, output_df):
variables_list = list(
mod_raw_data_df.columns
) #local var and .columns preferred to minimize use of global scope
wb = Workbook()
ws = wb.active
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols = [x for x in variables_list]
header_rows = [x for x in variables_list]
ws.append([""] + header_cols)
for ind, var in enumerate(header_rows):
ws.cell(row=ind + 2, column=1).value = var
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_rows) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
outside_loop_var = ws.cell(row=outside_loop_ind, column=1).value
elif global_vars.corr_table_triangle == "Lower triangle":
outside_loop_var = ws.cell(row=1, column=outside_loop_ind).value
for inside_loop_ind in range(inside_loop_ind_start,
len(header_cols) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
inside_loop_var = ws.cell(row=1, column=inside_loop_ind).value
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_var = ws.cell(row=inside_loop_ind, column=1).value
if outside_loop_var == inside_loop_var:
ws.cell(row=outside_loop_ind, column=inside_loop_ind).value = 1
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) | (
(output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
ws.cell(row=outside_loop_ind,
column=inside_loop_ind).value = r
elif global_vars.corr_table_triangle == "Lower triangle":
ws.cell(row=inside_loop_ind,
column=outside_loop_ind).value = r
if global_vars.corr_table_triangle != "Both":
inside_loop_ind_start += 1
for row in range(1, len(header_rows) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1] + ws["A"]:
cell.font = global_vars.font_header
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA,
bottom=global_vars.border_APA)
for cell in ws[len(header_rows) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
table_notes = [
"Correlation coefficient used: {}".format(
list(global_vars.master_dict.keys())[list(
global_vars.master_dict.values()).index(
global_vars.raw_corr_type)])
]
table_notes.append("**p < 0.01")
table_notes.append("*p < {}".format(global_vars.alpha_threshold))
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def raw_corr_apa_table_withCIs_word(mod_raw_data_df, output_df):
variables_list = list(mod_raw_data_df.columns)
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols = [x for x in variables_list]
header_rows = [x for x in variables_list]
# this adds an empty column where the significance signs will be placed for better presentation
# then adds empty rows for the CIs
# the code looks slightly wrong as it return a None array but it works
[header_cols.insert(x, "") for x in range(1, len(header_cols) * 2, 2)]
[header_rows.insert(x, "") for x in range(1, len(header_rows) * 2, 2)]
doc = Document()
table_rows_len = len(header_rows) + 1
table_cols_len = len(header_cols) + 1
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
for ind, var in enumerate([""] + header_cols):
table.cell(row_idx=0, col_idx=ind).text = var
for ind, var in enumerate([""] + header_rows):
table.cell(row_idx=ind, col_idx=0).text = var
if global_vars.corr_table_triangle == "Upper triangle":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_rows_len, 2):
outside_loop_var = table.cell(row_idx=outside_loop_ind,
col_idx=0).text
for inside_loop_ind in range(inside_loop_ind_start, table_cols_len,
2):
inside_loop_var = table.cell(row_idx=0,
col_idx=inside_loop_ind).text
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) | (
(output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(df_filtered["CI_high"])
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=outside_loop_ind,
col_idx=inside_loop_ind).text = r
table.cell(row_idx=outside_loop_ind,
col_idx=inside_loop_ind + 1).text = sign
table.cell(row_idx=outside_loop_ind + 1,
col_idx=inside_loop_ind
).text = "[" + ci_low + ", " + ci_high + "]"
inside_loop_ind_start += 2
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_cols_len, 2):
outside_loop_var = table.cell(row_idx=0,
col_idx=outside_loop_ind).text
for inside_loop_ind in range(inside_loop_ind_start, table_rows_len,
2):
inside_loop_var = table.cell(row_idx=inside_loop_ind,
col_idx=0).text
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) | (
(output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(df_filtered["CI_high"])
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = r
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind + 1).text = sign
table.cell(row_idx=inside_loop_ind + 1,
col_idx=outside_loop_ind
).text = "[" + ci_low + ", " + ci_high + "]"
inside_loop_ind_start += 2
elif global_vars.corr_table_triangle == "Both":
inside_loop_ind_start = 1
for outside_loop_ind in range(1, table_cols_len, 2):
outside_loop_var = table.cell(row_idx=0,
col_idx=outside_loop_ind).text
for inside_loop_ind in range(inside_loop_ind_start, table_rows_len,
2):
inside_loop_var = table.cell(row_idx=inside_loop_ind,
col_idx=0).text
if outside_loop_var == inside_loop_var:
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = "1"
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[
((output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) |
((output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(
df_filtered["CI_high"])
r = helper_funcs.correlations_format_val(r, p)
if "_" in r:
r, sign = r.split("_")
else:
sign = ""
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind).text = r
table.cell(row_idx=inside_loop_ind,
col_idx=outside_loop_ind + 1).text = sign
table.cell(row_idx=inside_loop_ind + 1,
col_idx=outside_loop_ind
).text = "[" + ci_low + ", " + ci_high + "]"
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell,
top=global_vars.border_APA_word,
bottom=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
for i in range(1, table_cols_len, 2):
table.cell(row_idx=0,
col_idx=i).merge(table.cell(row_idx=0, col_idx=i + 1))
table.cell(row_idx=0, col_idx=i).text = table.cell(
row_idx=0, col_idx=i
).text[:
-1] # meging cells adds a paragraph break at the end; this gets rid of it
for i in range(1, table_rows_len, 2):
table.cell(row_idx=i,
col_idx=0).merge(table.cell(row_idx=i + 1, col_idx=0))
table.cell(row_idx=i, col_idx=0).text = table.cell(
row_idx=i, col_idx=0
).text[:
-1] # meging cells adds a paragraph break at the end; this gets rid of it
for row in range(2, table_rows_len, 2):
for col in range(1, table_cols_len, 2):
table.cell(row_idx=row, col_idx=col).merge(
table.cell(row_idx=row, col_idx=col + 1))
table.cell(row_idx=row,
col_idx=col).alignment = WD_ALIGN_PARAGRAPH.CENTER
helper_funcs.word_style(table.cell(row_idx=row, col_idx=col),
size=9)
for cell in table.rows[0].cells:
helper_funcs.word_style(cell, italic=True)
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
cell.vertical_alignment = WD_ALIGN_VERTICAL.TOP
for cell in table.columns[0].cells:
helper_funcs.word_style(cell, italic=True)
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for row in range(0, table_rows_len):
for col in range(1, table_cols_len):
cell = table.cell(row_idx=row, col_idx=col)
if col >= 1:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].paragraph_format.space_after = Inches(0)
cell.paragraphs[0].paragraph_format.space_before = Inches(0)
cell.paragraphs[0].paragraph_format.line_spacing = 1
for row in range(1, table_rows_len, 2):
for col in range(1, table_cols_len, 2):
table.cell(
row_idx=row, col_idx=col
).paragraphs[0].paragraph_format.right_indent = Inches(-0.08)
table.cell(
row_idx=row, col_idx=col +
1).paragraphs[0].paragraph_format.left_indent = Inches(-0.06)
table.cell(
row_idx=row,
col_idx=col).paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.RIGHT
table.cell(row_idx=row, col_idx=col +
1).paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.LEFT
doc = helper_funcs.set_autofit(doc)
para = doc.add_paragraph("** ")
para.add_run("p").italic = True
para.add_run(" < 0.01")
para.add_run().add_break()
para.add_run("* ")
para.add_run("p").italic = True
para.add_run(" < {}".format(global_vars.alpha_threshold))
doc.add_paragraph("Correlation coefficient used: {}".format(
list(global_vars.master_dict.keys())[list(
global_vars.master_dict.values()).index(
global_vars.raw_corr_type)]))
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def raw_corr_apa_table_withCIs_excel(mod_raw_data_df, output_df):
variables_list = list(
mod_raw_data_df.columns
) # local var and .columns preferred to minimize use of global scope
wb = Workbook()
ws = wb.active
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols = [x for x in variables_list]
header_rows = [x for x in variables_list]
# this adds an empty row where the CIs will be
# the code looks slightly wrong as it return a None array but it works
[header_rows.insert(x, "") for x in range(1, len(header_rows) * 2, 2)]
ws.append([""] + header_cols)
for ind, var in enumerate(header_rows):
ws.cell(row=ind + 2, column=1).value = var
if global_vars.corr_table_triangle == "Upper triangle":
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_rows) + 2, 2):
outside_loop_var = ws.cell(row=outside_loop_ind, column=1).value
for inside_loop_ind in range(inside_loop_ind_start,
len(header_cols) + 2):
inside_loop_var = ws.cell(row=1, column=inside_loop_ind).value
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) | (
(output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(df_filtered["CI_high"])
ws.cell(row=outside_loop_ind, column=inside_loop_ind).value = r
ws.cell(row=outside_loop_ind + 1, column=inside_loop_ind
).value = "[" + ci_low + ", " + ci_high + "]"
inside_loop_ind_start += 1
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_cols) + 2):
outside_loop_var = ws.cell(row=1, column=outside_loop_ind).value
for inside_loop_ind in range(inside_loop_ind_start,
len(header_rows) + 2, 2):
inside_loop_var = ws.cell(row=inside_loop_ind, column=1).value
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[(
(output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) | (
(output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(df_filtered["CI_high"])
ws.cell(row=inside_loop_ind, column=outside_loop_ind).value = r
ws.cell(row=inside_loop_ind + 1, column=outside_loop_ind
).value = "[" + ci_low + ", " + ci_high + "]"
inside_loop_ind_start += 2
elif global_vars.corr_table_triangle == "Both":
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_cols) + 2):
outside_loop_var = ws.cell(row=1, column=outside_loop_ind).value
for inside_loop_ind in range(inside_loop_ind_start,
len(header_rows) + 2, 2):
inside_loop_var = ws.cell(row=inside_loop_ind, column=1).value
if outside_loop_var == inside_loop_var:
ws.cell(row=inside_loop_ind,
column=outside_loop_ind).value = "1"
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[
((output_df["Variable1"] == outside_loop_var) &
(output_df["Variable2"] == inside_loop_var)) |
((output_df["Variable1"] == inside_loop_var) &
(output_df["Variable2"] == outside_loop_var))].iloc[0]
r = df_filtered["Correlation_Coefficient"]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
ci_low, ci_high = helper_funcs.correlations_format_val(
df_filtered["CI_low"]
), helper_funcs.correlations_format_val(
df_filtered["CI_high"])
ws.cell(row=inside_loop_ind,
column=outside_loop_ind).value = r
ws.cell(row=inside_loop_ind + 1, column=outside_loop_ind
).value = "[" + ci_low + ", " + ci_high + "]"
for row in range(2, len(header_rows) + 1, 2):
ws.merge_cells(start_row=row,
start_column=1,
end_row=row + 1,
end_column=1)
if global_vars.corr_table_triangle == "Both":
for col in range(2, len(header_cols) + 2):
ws.merge_cells(start_row=col * 2 - 2,
start_column=col,
end_row=col * 2 - 1,
end_column=col)
for row in range(1, len(header_rows) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1] + ws["A"]:
cell.font = global_vars.font_header
for row in range(3, len(header_rows) + 2, 2):
for cell in ws[row]:
cell.font = Font(size=9)
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA,
bottom=global_vars.border_APA)
for cell in ws[len(header_rows) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
table_notes = [
"Correlation coefficient used: {}".format(
list(global_vars.master_dict.keys())[list(
global_vars.master_dict.values()).index(
global_vars.raw_corr_type)])
]
table_notes.append("**p < 0.01")
table_notes.append("*p < {}".format(global_vars.alpha_threshold))
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def summ_corr_apa_table_excel(mod_raw_data_df, output_df):
# unique vars in var1 given by user's order and here ONLY adding vars from col 2 that are NOT in var 1
variables_list = list(output_df[global_vars.summ_corr_varOne].unique()) + list(set(output_df[global_vars.summ_corr_varTwo].unique()) - set(output_df[global_vars.summ_corr_varOne].unique()))
if global_vars.corr_table_triangle == "Upper triangle":
header_cols = variables_list[1:]
header_rows = variables_list[:-1]
elif global_vars.corr_table_triangle == "Lower triangle":
header_cols = variables_list[:-1]
header_rows = variables_list[1:]
elif global_vars.corr_table_triangle == "Both":
header_cols, header_rows = variables_list, variables_list
wb = Workbook()
ws = wb.active
ws.append([""] + header_cols)
for ind,var in enumerate(header_rows):
ws.cell(row=ind+2, column=1).value = var
inside_loop_ind_start = 2
for outside_loop_ind in range(2, len(header_rows) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
outside_loop_var = ws.cell(row=outside_loop_ind, column=1).value
elif global_vars.corr_table_triangle == "Lower triangle":
outside_loop_var = ws.cell(row=1, column=outside_loop_ind).value
for inside_loop_ind in range(inside_loop_ind_start, len(header_cols) + 2):
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
inside_loop_var = ws.cell(row=1, column=inside_loop_ind).value
elif global_vars.corr_table_triangle == "Lower triangle":
inside_loop_var = ws.cell(row=inside_loop_ind, column=1).value
if outside_loop_var == inside_loop_var:
ws.cell(row=outside_loop_ind, column=inside_loop_ind).value = 1
else:
# here query method is not preferred as it is not only slower as it is much smaller dataset but also cannot refer to two different vaiables (colname and val)
df_filtered = output_df[((output_df[global_vars.summ_corr_varOne]==outside_loop_var) & (output_df[global_vars.summ_corr_varTwo]==inside_loop_var)) | ((output_df[global_vars.summ_corr_varOne]==inside_loop_var) & (output_df[global_vars.summ_corr_varTwo]==outside_loop_var))].iloc[0]
r = df_filtered[global_vars.summ_corr_coeff]
p = df_filtered["adjusted_pvalues"]
r = helper_funcs.correlations_format_val(r, p)
if global_vars.corr_table_triangle == "Upper triangle" or global_vars.corr_table_triangle == "Both":
ws.cell(row=outside_loop_ind, column=inside_loop_ind).value = r
elif global_vars.corr_table_triangle == "Lower triangle":
ws.cell(row=inside_loop_ind, column=outside_loop_ind).value = r
if global_vars.corr_table_triangle != "Both":
inside_loop_ind_start += 1
for row in range(1, len(header_rows) + 2):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1]:
cell.font = global_vars.font_header
for row in range(2, len(header_rows) + 2):
ws.cell(row=row, column=1).font = global_vars.font_header
for cell in ws[len(header_rows) + 1]:
cell.border = Border(bottom=global_vars.border_APA)
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA, bottom=global_vars.border_APA)
table_notes = ["**p < 0.01", "*p < {}".format(global_vars.alpha_threshold)]
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def spss_indttest_apa_table_word(mod_raw_data_df, output_df):
# very similar to raw_corr_indttest_apa_table func but separate as might be udpated/adjusted in the future
output_df.drop(columns=["pvalues"], inplace=True)
pd.options.mode.chained_assignment = None
output_df[list(output_df.columns)[7:-1]] = output_df[list(
output_df.columns)[7:-1]].applymap(lambda x: "{:.2f}".format(x))
output_df["adjusted_pvalues"] = output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
doc = Document()
table_rows_len = len(output_df) + 2
table_cols_len = len(output_df.columns)
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
table.cell(row_idx=0, col_idx=0).text = "Variable"
table.cell(row_idx=0, col_idx=0).merge(table.cell(row_idx=1, col_idx=0))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=0), italic=True)
table.cell(row_idx=0, col_idx=1).text = "All, n=?"
table.cell(row_idx=0, col_idx=1).merge(table.cell(row_idx=0, col_idx=2))
if global_vars.spss_indttest_nOne != -1:
n1_label = global_vars.spss_indttest_nOne
else:
n1_label = "?"
table.cell(row_idx=0, col_idx=3).text = "{g}, n={n}".format(
g=global_vars.spss_indttest_groupOneLabel, n=n1_label)
table.cell(row_idx=0, col_idx=3).merge(table.cell(row_idx=0, col_idx=4))
if global_vars.spss_indttest_nOne != -1:
n2_label = global_vars.spss_indttest_nTwo
else:
n2_label = "?"
table.cell(row_idx=0, col_idx=5).text = "{g}, n={n}".format(
g=global_vars.spss_indttest_groupTwoLabel, n=n2_label)
table.cell(row_idx=0, col_idx=5).merge(table.cell(row_idx=0, col_idx=6))
table.cell(row_idx=0, col_idx=7).text = "df"
table.cell(row_idx=0, col_idx=7).merge(table.cell(row_idx=1, col_idx=7))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=7), italic=True)
table.cell(row_idx=0, col_idx=8).text = "t"
table.cell(row_idx=0, col_idx=8).merge(table.cell(row_idx=1, col_idx=8))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=8), italic=True)
table.cell(row_idx=0, col_idx=9).text = global_vars.effect_size_choice
if global_vars.effect_size_choice != "None": # otherwise cant remove with delete columns below if merged; see helper_funcs.delete_columns_word func notes
table.cell(row_idx=0, col_idx=9).merge(table.cell(row_idx=1,
col_idx=9))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=9), italic=True)
table.cell(row_idx=0, col_idx=10).text = "p"
table.cell(row_idx=0, col_idx=10).merge(table.cell(row_idx=1, col_idx=10))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=10), italic=True)
for col in range(1, 6, 2):
table.cell(row_idx=1, col_idx=col).text = "M"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col),
italic=True)
table.cell(row_idx=1, col_idx=col + 1).text = "SD"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col + 1),
italic=True)
for row in range(2, table_rows_len):
for col in range(0, table_cols_len):
table.cell(row_idx=row, col_idx=col).text = output_df.iloc[row - 2,
col]
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[2].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
if global_vars.effect_size_choice == "None":
helper_funcs.delete_columns_word(table, [9])
doc = helper_funcs.set_autofit(doc)
doc.add_paragraph(
"Means and Standard Deviations cannot be read from the SPSS table. Please add them yourself or remove those columns if they are not needed."
)
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)
def spss_indttest_apa_table_excel(mod_raw_data_df, output_df):
output_df.drop(columns=["pvalues"], inplace=True)
pd.options.mode.chained_assignment = None
output_df[list(output_df.columns)[7:-1]] = output_df[list(
output_df.columns)[7:-1]].applymap(lambda x: "{:.2f}".format(x))
output_df["adjusted_pvalues"] = output_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
wb = Workbook()
ws = wb.active
ws.cell(row=1, column=1).value = "Variable"
ws.merge_cells('A1:A2')
ws.cell(row=1, column=1).font = global_vars.font_header
ws.cell(row=1, column=2).value = "All, n=?"
ws.merge_cells('B1:C1')
if global_vars.spss_indttest_nOne != -1:
n1_label = global_vars.spss_indttest_nOne
else:
n1_label = "?"
ws.cell(row=1, column=4).value = "{g}, n={n}".format(
g=global_vars.spss_indttest_groupOneLabel, n=n1_label)
ws.merge_cells('D1:E1')
if global_vars.spss_indttest_nOne != -1:
n2_label = global_vars.spss_indttest_nTwo
else:
n2_label = "?"
ws.cell(row=1, column=6).value = "{g}, n={n}".format(
g=global_vars.spss_indttest_groupTwoLabel, n=n2_label)
ws.merge_cells('F1:G1')
ws.cell(row=1, column=8).value = "df"
ws.merge_cells('H1:H2')
ws.cell(row=1, column=8).font = global_vars.font_header
ws.cell(row=1, column=9).value = "t"
ws.merge_cells('I1:I2')
ws.cell(row=1, column=9).font = global_vars.font_header
ws.cell(row=1, column=10).value = global_vars.effect_size_choice
ws.merge_cells('J1:J2')
ws.cell(row=1, column=10).font = global_vars.font_header
ws.cell(row=1, column=11).value = "p"
ws.merge_cells('K1:K2')
ws.cell(row=1, column=11).font = global_vars.font_header
for col in range(2, 7, 2):
ws.cell(row=2, column=col).value = "M"
ws.cell(row=2, column=col).font = global_vars.font_header
ws.cell(row=2, column=col + 1).value = "SD"
ws.cell(row=2, column=col + 1).font = global_vars.font_header
for row in dataframe_to_rows(output_df, index=False, header=False):
ws.append(row)
for row in range(1, len(output_df) + 3):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA)
for cell in ws[2] + ws[len(output_df) + 2]:
cell.border = Border(bottom=global_vars.border_APA)
if global_vars.effect_size_choice == "None":
ws.delete_cols(10)
table_notes = [
"Means and Standard Deviations cannot be read from the SPSS table. Please add them yourself or remove those columns if they are not needed."
]
helper_funcs.add_table_notes(ws, table_notes)
helper_funcs.savefile(wb=wb)
def raw_indttest_apa_table_excel(mod_raw_data_df, output_df):
apa_table_df = output_df[[
"Variable", "All_Mean", "All_SD",
global_vars.raw_indttest_grouplevel1 + "_Mean",
global_vars.raw_indttest_grouplevel1 + "_SD",
global_vars.raw_indttest_grouplevel2 + "_Mean",
global_vars.raw_indttest_grouplevel2 + "_SD", "Degrees_of_Freedom",
"t", global_vars.effect_size_choice, "adjusted_pvalues"
]]
# the two operations below are correct so the SettingWithCopyWarning pandas error is supressed temporarily
pd.options.mode.chained_assignment = None
apa_table_df[list(apa_table_df.columns)[1:-1]] = apa_table_df[list(
apa_table_df.columns)[1:-1]].applymap(lambda x: "{:.2f}".format(x))
apa_table_df["adjusted_pvalues"] = apa_table_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
wb = Workbook()
ws = wb.active
ws.cell(row=1, column=1).value = "Variable"
ws.merge_cells('A1:A2')
ws.cell(row=1, column=1).font = global_vars.font_header
ws.cell(row=1, column=2).value = "All, n={}".format(output_df.iloc[0, 1])
ws.merge_cells('B1:C1')
ws.cell(row=1, column=4).value = "{g}, n={n}".format(
g=global_vars.raw_indttest_grouplevel1, n=output_df.iloc[0, 4])
ws.merge_cells('D1:E1')
ws.cell(row=1, column=6).value = "{g}, n={n}".format(
g=global_vars.raw_indttest_grouplevel2, n=output_df.iloc[0, 7])
ws.merge_cells('F1:G1')
ws.cell(row=1, column=8).value = "df"
ws.merge_cells('H1:H2')
ws.cell(row=1, column=8).font = global_vars.font_header
ws.cell(row=1, column=9).value = "t"
ws.merge_cells('I1:I2')
ws.cell(row=1, column=9).font = global_vars.font_header
ws.cell(row=1, column=10).value = global_vars.effect_size_choice
ws.merge_cells('J1:J2')
ws.cell(row=1, column=10).font = global_vars.font_header
ws.cell(row=1, column=11).value = "p"
ws.merge_cells('K1:K2')
ws.cell(row=1, column=11).font = global_vars.font_header
for col in range(2, 7, 2):
ws.cell(row=2, column=col).value = "M"
ws.cell(row=2, column=col).font = global_vars.font_header
ws.cell(row=2, column=col + 1).value = "SD"
ws.cell(row=2, column=col + 1).font = global_vars.font_header
for row in dataframe_to_rows(apa_table_df, index=False, header=False):
ws.append(row)
for row in range(1, len(apa_table_df) + 3):
for cell in ws[row]:
cell.alignment = global_vars.alignment_center
for cell in ws[1]:
cell.border = Border(top=global_vars.border_APA)
for cell in ws[2] + ws[len(apa_table_df) + 2]:
cell.border = Border(bottom=global_vars.border_APA)
if global_vars.effect_size_choice == "None":
ws.delete_cols(10)
helper_funcs.add_table_notes(ws, [])
helper_funcs.savefile(wb=wb)
def raw_indttest_apa_table_word(mod_raw_data_df, output_df):
apa_table_df = output_df[[
"Variable", "All_Mean", "All_SD",
global_vars.raw_indttest_grouplevel1 + "_Mean",
global_vars.raw_indttest_grouplevel1 + "_SD",
global_vars.raw_indttest_grouplevel2 + "_Mean",
global_vars.raw_indttest_grouplevel2 + "_SD", "Degrees_of_Freedom",
"t", global_vars.effect_size_choice, "adjusted_pvalues"
]]
# the two operations below are correct so the SettingWithCopyWarning pandas error is supressed temporarily
pd.options.mode.chained_assignment = None
apa_table_df[list(apa_table_df.columns)[1:-1]] = apa_table_df[list(
apa_table_df.columns)[1:-1]].applymap(lambda x: "{:.2f}".format(x))
apa_table_df["adjusted_pvalues"] = apa_table_df["adjusted_pvalues"].map(
helper_funcs.pvalue_formatting)
pd.options.mode.chained_assignment = "warn"
doc = Document()
table_rows_len = len(apa_table_df) + 2
table_cols_len = len(apa_table_df.columns)
table = doc.add_table(rows=table_rows_len, cols=table_cols_len)
table.cell(row_idx=0, col_idx=0).text = "Variable"
table.cell(row_idx=0, col_idx=0).merge(table.cell(row_idx=1, col_idx=0))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=0), italic=True)
table.cell(row_idx=0,
col_idx=1).text = "All, n={}".format(output_df.iloc[0, 1])
table.cell(row_idx=0, col_idx=1).merge(table.cell(row_idx=0, col_idx=2))
table.cell(row_idx=0, col_idx=3).text = "{g}, n={n}".format(
g=global_vars.raw_indttest_grouplevel1, n=output_df.iloc[0, 4])
table.cell(row_idx=0, col_idx=3).merge(table.cell(row_idx=0, col_idx=4))
table.cell(row_idx=0, col_idx=5).text = "{g}, n={n}".format(
g=global_vars.raw_indttest_grouplevel2, n=output_df.iloc[0, 7])
table.cell(row_idx=0, col_idx=5).merge(table.cell(row_idx=0, col_idx=6))
table.cell(row_idx=0, col_idx=7).text = "df"
table.cell(row_idx=0, col_idx=7).merge(table.cell(row_idx=1, col_idx=7))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=7), italic=True)
table.cell(row_idx=0, col_idx=8).text = "t"
table.cell(row_idx=0, col_idx=8).merge(table.cell(row_idx=1, col_idx=8))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=8), italic=True)
table.cell(row_idx=0, col_idx=9).text = global_vars.effect_size_choice
if global_vars.effect_size_choice != "None": # otherwise cant remove with delete columns below if merged; see helper_funcs.delete_columns_word func notes
table.cell(row_idx=0, col_idx=9).merge(table.cell(row_idx=1,
col_idx=9))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=9), italic=True)
table.cell(row_idx=0, col_idx=10).text = "p"
table.cell(row_idx=0, col_idx=10).merge(table.cell(row_idx=1, col_idx=10))
helper_funcs.word_style(table.cell(row_idx=0, col_idx=10), italic=True)
for col in range(1, 6, 2):
table.cell(row_idx=1, col_idx=col).text = "M"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col),
italic=True)
table.cell(row_idx=1, col_idx=col + 1).text = "SD"
helper_funcs.word_style(table.cell(row_idx=1, col_idx=col + 1),
italic=True)
for row in range(2, table_rows_len):
for col in range(0, table_cols_len):
table.cell(row_idx=row,
col_idx=col).text = apa_table_df.iloc[row - 2, col]
for row in range(0, table_rows_len):
for cell in table.rows[row].cells:
cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
cell.paragraphs[0].alignment = WD_ALIGN_PARAGRAPH.CENTER
for cell in table.rows[0].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[2].cells:
helper_funcs.set_cell_border(cell, top=global_vars.border_APA_word)
for cell in table.rows[table_rows_len - 1].cells:
helper_funcs.set_cell_border(cell, bottom=global_vars.border_APA_word)
if global_vars.effect_size_choice == "None":
helper_funcs.delete_columns_word(table, [9])
doc = helper_funcs.set_autofit(doc)
helper_funcs.add_correction_message_word(doc)
helper_funcs.savefile(doc=doc)