|
| 1 | +# Excel Data Frame |
| 2 | +import pandas as pd |
| 3 | +from openpyxl.workbook import Workbook |
| 4 | + |
| 5 | +dataframe_excel = pd.read_excel('excel/regiondata.xlsx') |
| 6 | + |
| 7 | +print(dataframe_excel) |
| 8 | + |
| 9 | +# CSV Data Frame |
| 10 | +dataframe_csv = pd.read_csv('excel/some_names.csv') |
| 11 | + |
| 12 | +print(dataframe_csv) |
| 13 | + |
| 14 | +# Setting Column Names |
| 15 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 16 | + |
| 17 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 18 | +print(dataframe_csv) |
| 19 | + |
| 20 | +# Pandas CSV to Excel |
| 21 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 22 | + |
| 23 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 24 | +print(dataframe_csv) |
| 25 | + |
| 26 | +dataframe_csv.to_excel('excel/some_names_modified.xlsx') |
| 27 | + |
| 28 | +# Text File Data Frame |
| 29 | +dataframe_txt = pd.read_csv('excel/some_data.txt', delimiter='\t') |
| 30 | + |
| 31 | +print(dataframe_txt) |
| 32 | + |
| 33 | +# Work With Columns In Pandas |
| 34 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 35 | + |
| 36 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 37 | +print(dataframe_csv.columns) |
| 38 | + |
| 39 | + |
| 40 | +# take the First Name index and this prints out all the values in the First Name column |
| 41 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 42 | + |
| 43 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 44 | +print(dataframe_csv['First']) |
| 45 | + |
| 46 | +# access multiple column’s data |
| 47 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 48 | + |
| 49 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 50 | +print(dataframe_csv[['Address', 'State']]) |
| 51 | + |
| 52 | +# look at the Zip column, but only the first two results |
| 53 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 54 | + |
| 55 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 56 | +print(dataframe_csv['Zip'][0:2]) |
| 57 | + |
| 58 | +# Work With Rows In Pandas |
| 59 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 60 | + |
| 61 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 62 | +print(dataframe_csv.iloc[2]) |
| 63 | + |
| 64 | +# Locate exact cell |
| 65 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 66 | + |
| 67 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 68 | +print(dataframe_csv.iloc[3, 2]) |
| 69 | + |
| 70 | +# Saving Extracted Data |
| 71 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 72 | + |
| 73 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 74 | + |
| 75 | +extracted_data = dataframe_csv[['First', 'Last', 'City']] |
| 76 | + |
| 77 | +stored = extracted_data.to_excel('extracted_data.xlsx', index=None) |
| 78 | + |
| 79 | +# Filter And Sort Data Using Pandas |
| 80 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 81 | + |
| 82 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 83 | + |
| 84 | +print(dataframe_csv[dataframe_csv['City'] == 'Worthington']) |
| 85 | + |
| 86 | +# checks for all rows where the City is Kentwood *and* the First column has a value of Sam. |
| 87 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 88 | + |
| 89 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 90 | + |
| 91 | +print(dataframe_csv[(dataframe_csv['City'] == 'Kentwood') & (dataframe_csv['First'] == 'Sam')]) |
| 92 | + |
| 93 | +# drop columns using the .drop() function. |
| 94 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 95 | + |
| 96 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 97 | + |
| 98 | +drop = ['Address', 'Population'] |
| 99 | +dataframe_csv.drop(columns=drop, inplace=True) |
| 100 | + |
| 101 | +print(dataframe_csv) |
| 102 | + |
| 103 | +# check to see if the State column has a value of OH, and if it does, go ahead and set the new column we defined to True. |
| 104 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 105 | + |
| 106 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 107 | + |
| 108 | +drop = ['Address', 'Population'] |
| 109 | +dataframe_csv.drop(columns=drop, inplace=True) |
| 110 | + |
| 111 | +dataframe_csv['T or F'] = False |
| 112 | +dataframe_csv.loc[dataframe_csv['State'] == 'OH', 'T or F'] = True |
| 113 | + |
| 114 | +print(dataframe_csv) |
| 115 | + |
| 116 | +# use the .sort_values() method to sort the data on a particular column |
| 117 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 118 | + |
| 119 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 120 | + |
| 121 | +print(dataframe_csv.sort_values('First')) |
| 122 | + |
| 123 | +# To sort the data in the other direction, just add ascending=False as the second argument |
| 124 | +dataframe_csv = pd.read_csv('excel/some_names.csv', header=None) |
| 125 | + |
| 126 | +dataframe_csv.columns = ['First', 'Last', 'Address', 'City', 'State', 'Zip', 'Population'] |
| 127 | + |
| 128 | +print(dataframe_csv.sort_values('First', ascending=False)) |
| 129 | + |
| 130 | +# Controlling Excel Directly With Openpyxl |
| 131 | +import openpyxl |
| 132 | + |
| 133 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 134 | + |
| 135 | +print(type(workbook)) |
| 136 | + |
| 137 | +# How To Access Worksheets |
| 138 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 139 | +sheet = workbook['Sheet1'] |
| 140 | + |
| 141 | +print(type(sheet)) |
| 142 | + |
| 143 | +# check what names exist with a simple call to .sheetnames. |
| 144 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 145 | +sheetnames = workbook.sheetnames |
| 146 | + |
| 147 | +print(sheetnames) |
| 148 | + |
| 149 | +# Access Cells In Sheets |
| 150 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 151 | +sheet = workbook['Sheet1'] |
| 152 | +cell = sheet['A3'] |
| 153 | + |
| 154 | +print(cell.value) |
| 155 | + |
| 156 | +# access a cell using the .cell() method and passing both the row and column as integers |
| 157 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 158 | +sheet = workbook['Sheet1'] |
| 159 | +cell = sheet.cell(row=4, column=14) |
| 160 | + |
| 161 | +print(cell.value) |
| 162 | + |
| 163 | +# iterate over values in the sheet |
| 164 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 165 | +sheet = workbook['Sheet1'] |
| 166 | + |
| 167 | +for i in range(2, 7): |
| 168 | + cell = sheet.cell(row=i, column=1) |
| 169 | + print(cell.value) |
| 170 | + |
| 171 | +# use slicing to select a range of cells |
| 172 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 173 | +sheet = workbook['Sheet1'] |
| 174 | + |
| 175 | +cell_range = sheet['A1':'A3'] |
| 176 | + |
| 177 | +print(cell_range) |
| 178 | + |
| 179 | +# print out the number of items in a column |
| 180 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 181 | +sheet = workbook['Sheet1'] |
| 182 | + |
| 183 | +column_a = sheet['A'] |
| 184 | + |
| 185 | +print(len(column_a)) |
| 186 | + |
| 187 | +# show all of the cells that have values in row 1 |
| 188 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 189 | +sheet = workbook['Sheet1'] |
| 190 | + |
| 191 | +row_0 = sheet[1] |
| 192 | + |
| 193 | +print(row_0) |
| 194 | + |
| 195 | +# iterating through columns or rows |
| 196 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 197 | +sheet = workbook['Sheet1'] |
| 198 | + |
| 199 | +for row in sheet.iter_rows(min_row=1, max_col=3, max_row=2): |
| 200 | + for cell in row: |
| 201 | + print(cell) |
| 202 | + |
| 203 | +# Creating New Workbooks and Worksheets |
| 204 | +workbook = openpyxl.Workbook() |
| 205 | +worksheet = workbook.active |
| 206 | + |
| 207 | +worksheet2 = workbook.create_sheet('First Sheet') |
| 208 | +worksheet3 = workbook.create_sheet('Second Sheet') |
| 209 | + |
| 210 | +worksheet.title = 'My Awesome Sheet' |
| 211 | + |
| 212 | +print(workbook.sheetnames) |
| 213 | + |
| 214 | +# add some data to one of the Worksheets |
| 215 | +workbook = openpyxl.Workbook() |
| 216 | +worksheet = workbook.active |
| 217 | + |
| 218 | +worksheet2 = workbook.create_sheet('First Sheet') |
| 219 | +worksheet3 = workbook.create_sheet('Second Sheet') |
| 220 | + |
| 221 | +worksheet.title = 'My Awesome Sheet' |
| 222 | +worksheet['A1'] = 'Hello Openpyxl' |
| 223 | +workbook.save('excel/awesomeworkbook.xlsx') |
| 224 | + |
| 225 | +# How To Format Workbooks |
| 226 | +from openpyxl.styles import Font, Alignment, GradientFill |
| 227 | + |
| 228 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 229 | +sheet = workbook['Sheet1'] |
| 230 | +sheet.insert_rows(1, 2) |
| 231 | +sheet.merge_cells('A1:O2') |
| 232 | +cell = sheet['A1'] |
| 233 | +cell.font = Font(color='007742', size=20, italic=True) |
| 234 | +cell.value = 'Super Cool And Stylish Spreadsheet' |
| 235 | +cell.alignment = Alignment(horizontal='right', vertical='center') |
| 236 | +cell.fill = GradientFill(stop=('000000', 'ffffff')) |
| 237 | +workbook.save('excel/stylish.xlsx') |
| 238 | + |
| 239 | +# Named Styles In Openpyxl |
| 240 | +from openpyxl.styles import Font, Alignment, GradientFill, NamedStyle, Side, Border, PatternFill |
| 241 | + |
| 242 | +workbook = openpyxl.load_workbook('excel/stock_options.xlsx') |
| 243 | +sheet = workbook['Sheet1'] |
| 244 | +sheet.insert_rows(1, 2) |
| 245 | +sheet.merge_cells('A1:O2') |
| 246 | +cell = sheet['A1'] |
| 247 | +cell.font = Font(color='007742', size=20, italic=True) |
| 248 | +cell.value = 'Super Cool And Stylish Spreadsheet' |
| 249 | +cell.alignment = Alignment(horizontal='right', vertical='center') |
| 250 | +cell.fill = GradientFill(stop=('000000', 'ffffff')) |
| 251 | + |
| 252 | +highlight = NamedStyle(name='highlight') |
| 253 | +highlight.font = Font(bold=True) |
| 254 | +bd = Side(style='thick', color='000000') |
| 255 | +highlight.border = Border(left=None, top=bd, right=None, bottom=bd) |
| 256 | +highlight.fill = PatternFill('solid', fgColor='fde295') |
| 257 | + |
| 258 | +for cell in sheet['3:3']: |
| 259 | + cell.style = highlight |
| 260 | + |
| 261 | +workbook.save('excel/stylish.xlsx') |
| 262 | + |
0 commit comments