IBM Switch 15 Instrukcja Użytkownika Strona 111
- Strona / 270
- Spis treści
- BOOKMARKI
Oceniono. / 5. Na podstawie oceny klientów
101
Handling Missing Values
In general terms, there are two approa ches you can follow:
You can exclude fields or re cords with missing values
You can impute, replace, or coerce missing values using a variety of m ethods
Both of these approaches can be largely automated using the Data Audit node. For example, you
can generate a Filter node that excludes fields with too m any missing values to be useful in
modeling, and generate a Supernode that imputes missing values for any or all of the fields that
remain. This is where the real power of the audit comes in, allowing you not only to assess the
current state of your data , but to take action based on the assessment.
Handling Records with Missing Values
If the majority of missing val ue s is concentrated in a small number of records, you can just
exclude those records. For example , a bank usu ally keeps detailed and complete record s on
its loan customers. If, h owever, the bank is less restricti ve in approving loans for its own staff
members, data gathered for staff loans is likely to have several blank fields. In such a case, there
are two options for hand ling these missing values:
You can use a Select node to remove the staff records.
If the data s et is large, you can discard all records with blanks.
Handling Fields with Missing Values
If the majority of missing values is concentrated in a small numb er of fields, you c an address them
at the field level rather than at the record level. This approach also a llows you to experiment with
the relativ e importance of particular fields before deciding on an approach for handling missing
values. If a field is unimportant in modeling, it probably is not worth keeping, regardless of how
many missing value s it h as.
For example, a market research company may colle ct data from a general questionnaire
containing 50 questions. Two of the questions address age and political persuasion, information
that many people are re luctant to give. In this c ase, Age and Political_persuasion have many
missing values.
Field Measurement Level
In dete r mining which method to use, you sho uld also conside r the measurement lev el of fields
with missing values.
Numeric fields.
For numeric field typ es, s uch as Continuous, you should always eliminate any
non-numeric values before building a model, be cause many models will not function if bla nks are
included in numeric fields.
Categorical fields.
For categorical field s
, such as Nominal and Flag, alte r ing missing values is not
necessary but w ill increase the accuracy of the mo del. For example, a model that uses the field Sex
will still function with meaningless valu es, such as Y and Z, but removing all values other than M
and F will increase the accuracy of the model
.
- About IBM Bu 3
- Contents 4
- 4 Understandin 5
- 5 Building Streams 41 5
- 6 Handling Missing Values 99 5
- 8 CLEM Language Reference 127 6
- 10 Exporting to E 8
- 11 Projects and Reports 200 8
- Appendices 9
- B Unicode Support 248 9
- C Notices 249 10
- Index 252 10
- About IBM SPSS Modeler 11
- Chapter 1 12
- IBM SPSS Modeler Editions 13
- Application Examples 15
- Demos Folder 16
- New Features 17
- Chapter 2 18
- New Nodes in This Release 20
- IBM SPSS Modeler Premium 21
- IBM SPSS Modeler Overview 22
- Changing the Temp Directory 26
- -noshare 27
- Nodes Palette 28
- IBM SPSS Modeler Managers 29
- IBM SPSS Modeler Projects 30
- IBM SPSS Modeler Toolbar 31
- Chapter 3 32
- Customizing the Toolbar 33
- Using Shortcut Keys 36
- Printing 37
- Automating IBM SPSS Modeler 37
- Understanding Data Mining 39
- Assessing the Data 40
- Beware of noisy data 41
- A Strategy for Data Mining 42
- The CRISP-DM Process Model 42
- Types of Models 44
- Classification nodes 45
- Chapter 4 46
- Association Models 47
- Segmentation Models 48
- In-Database Mining Models 49
- IBM SPSS Statistics Models 49
- Further Information 49
- Data Mining Examples 50
- Building Streams 51
- Working with Nodes 52
- Adding Nodes to a Stream 53
- Connecting Nodes in a Stream 53
- To Manually Connect Nodes 54
- Bypassing Nodes in a Stream 55
- Disabling Nodes in a Stream 56
- Setting Options for Nodes 58
- Caching Options for Nodes 60
- Previewing Data in Nodes 62
- Working with Streams 63
- Setting Options for Streams 64
- Logging and status 65
- To Set Stream Options 65
- Decimal symbol 66
- Grouping symbol 66
- Encoding 66
- Ruleset Evaluation 66
- Figure 5-16 67
- Import date/time as 68
- Date format 68
- Time format 68
- Rollover days/mins 68
- Date baseline (1st Jan) 68
- Setting numb 69
- Calculations in 70
- Save As Default 70
- Enable stream rewriting 71
- Optimize SQL generation 71
- Display SQL 73
- Show status for records 74
- Minimum stream canvas width 74
- Minimum stream canvas height 74
- Chapter 5 76
- Figure 5-22 76
- Viewing Node Execution Times 77
- Terminal Node 78
- Node Label 78
- Node Id 78
- Execution Time(s) 78
- Turn off these prompts 80
- Globals available 82
- Node label contains 83
- Stream Descriptions 84
- General Stream Information 85
- Description and Comments 85
- Scoring Information 85
- Comments 85
- Running Streams 87
- Working with Models 88
- Operations Involving Comments 91
- To edit an existing comment 92
- To resize a comment text box 93
- To move an existing comment 93
- To delete a comment 93
- Listing Stream Comments 94
- Positioning buttons 95
- Comment Colors 95
- Annotations 96
- Tooltip text 97
- Keywords 97
- Saving Data Streams 98
- Saving Output 99
- Loading Files 100
- Mapping Data Streams 101
- Mapping Data to a Template 102
- Step 4: Check mapped fields 103
- Mapping between Streams 104
- Specifying Essential Fields 104
- Examining Mapped Fields 105
- Tips and Shortcuts 106
- Browse for files quickly 107
- Did you know that you can 108
- Handling Missing Values 109
- Field Measurement Level 111
- Numeric fields 111
- Categorical fields 111
- Screening or Removing Fields 112
- Expression 112
- Algorithm 112
- Note on Discarding Records 114
- Building CLEM Expressions 115
- CLEM exp 116
- Figure 7-2 117
- CLEM Examples 118
- Complex Expressions 119
- Special Functions 119
- Values and Data Types 120
- Expressions and Conditions 121
- Working with Strings 122
- Working with Numbers 124
- Working with Times and Dates 124
- Summarizing Multiple Fields 125
- Numeric Functions 126
- Generating Lists of Fields 126
- The Expression Builder 127
- Chapter 7 128
- Figure 7-5 128
- Expression Builder dialog box 128
- Creating Expressions 129
- Selecting Functions 130
- Multiple-response sets 131
- Recently used 131
- Parameters 131
- Global values 131
- Viewing or Selecting Values 132
- Find and Replace 133
- Matching Character Classes 135
- Predefined Character Classes 135
- Boundary Matches 135
- Boundary matchers Matches 136
- \z The end of the input 136
- CLEM Language Reference 137
- Integers 138
- Characters 138
- Chapter 8 140
- CLEM Operators 141
- Operator Precedence 142
- Functions Reference 143
- Information Functions 144
- Conversion Functions 145
- Comparison Functions 145
- Logical Functions 147
- Trigonometr 149
- Probability Functions 149
- Bitwise Integer Operations 150
- Random Functions 151
- String Functions 151
- SoundEx Functions 156
- Date and Time Functions 156
- Sequence Functions 160
- Examples 161
- Global Functions 165
- Special Fields 167
- Using IBM SPSS Modeler with a 168
- Repository 168
- Single Sign-On 169
- Connecting to the Repository 171
- Ensure secure connection 172
- User ID and password 172
- Provider 172
- Figure 9-4 173
- Setting Object Properties 174
- Save in 175
- File name 175
- Principal 178
- Permissions 178
- Select provider 179
- User list 179
- Storing Streams 180
- Storing Projects 180
- Storing Nodes 181
- Storing Output Objects 181
- Storing a model 182
- Storing a Models palette 182
- Selecting an Object Version 184
- Searching by Name 185
- Searching by Other Criteria 186
- Object Types 186
- Streams 186
- Modifying Repository Objects 187
- Deleting Repository Objects 188
- Viewing Folder Properties 189
- Version 192
- Edit Labels 192
- Permissions Tab 192
- Users And Groups 193
- To apply labels to the object 193
- Deploying Streams 194
- Stream Deployment Options 195
- Deployment type 196
- The Scoring Branch 198
- Model Refresh 200
- Single Model in Stream 201
- Multiple Models in Stream 201
- No Models in Stream 204
- To Export a Model 206
- Model Types Supporting PMML 208
- Database native models 209
- PMML Import 209
- Projects and Reports 210
- CRISP-DM View 211
- Building a Project 212
- Adding to a Project 213
- Setting Project Properties 215
- Annotating a Project 216
- To annotate a folder: 217
- Object Properties 218
- Generating a 219
- To generate a report: 220
- Output name 221
- Output to screen 221
- Output to file 221
- Filename 221
- Saving and 222
- Exporting Generated Reports 222
- Chapter 11 224
- Figure 11-11 224
- Customizing IBM SPSS Modeler 225
- Setting Default Directories 226
- Setting User Options 227
- Setting Display Options 230
- Setting PMML Export Options 231
- Export PMML 232
- Standard PMML Options 232
- User/Author Information 232
- Customizing the Nodes Palette 233
- Palette Name 234
- No. of nodes 234
- Sub Palettes 234
- Restore Defaults 234
- Creating a Palette Tab 235
- Creating a Subpalette 237
- Changing a Palette Tab View 238
- CEMI Node Management 239
- Streams and N 240
- Node Caches 241
- To Enable a Cache 242
- Caching Nodes in a Database 242
- Performance 243
- : Process Nodes 243
- Performance: Modeling Nodes 244
- Performance: CLEM Expressions 244
- Appendix 246
- Accessibility for Blind Users 247
- Keyboard Accessibility 248
- Node and Stream Shortcuts 249
- Appendix A 250
- Table Shortcuts 251
- Shortcuts for Comments 252
- Cluster Viewer only 253
- Start SPSS Modeler 253
- Ctrl+Down Arrow 253
- Right Arrow 253
- Using a Screen Reader 255
- Tips for Use 256
- Interferenc 257
- JAWS and Java 257
- Unicode Support 258
- Trademarks 260
Powiązane produkty i podręczniki dla Oprogramowanie IBM Switch 15
Oprogramowanie IBM DS6000 Instrukcja Użytkownika
(406 strony)
(406 strony)
Oprogramowanie IBM CDI5UG1107 Instrukcja Użytkownika
(178 strony)
(178 strony)
Sharp FO-NS2 manuali
Manuali dei proprietari e guide per l'utente per Software Sharp FO-NS2.
We fornisce 2 manuali pdf Sharp FO-NS2 per scaricare gratuitamente in base al tipo di documento: Manuale di Servizio, Manuale Utente
Komentarze do niniejszej Instrukcji