Skip to content

Commit 99a2f4a

Browse files
risenWrisenW
committed
format spacing
1 parent 51821fb commit 99a2f4a

3 files changed

Lines changed: 95 additions & 96 deletions

File tree

‎danfojs/src/core/get_dummies.js‎

Lines changed: 92 additions & 92 deletions
Original file line numberDiff line numberDiff line change
@@ -1,26 +1,26 @@
11
// import { Series } from "./series"
2-
import {DataFrame} from "./frame"
2+
import { DataFrame } from "./frame"
33
import { Utils } from "./utils"
44

55
const utils = new Utils
66

7-
function oneHot(in_data, prefix, prefix_sep){
7+
function oneHot(in_data, prefix, prefix_sep) {
88
let data_set = new Set(in_data);
99
let labels = Array.from(data_set);
1010
let prefix_labels = null;
11-
if(prefix){
12-
prefix_labels = labels.map((x)=>{
11+
if (prefix) {
12+
prefix_labels = labels.map((x) => {
1313
return prefix + prefix_sep + x
1414
})
15-
}else{
16-
prefix_labels = labels.map((x)=>{
15+
} else {
16+
prefix_labels = labels.map((x) => {
1717
return x
1818
})
1919
}
20-
20+
2121
let onehot_data = utils.__zeros(in_data.length, labels.length)
2222

23-
for(let i=0; i < in_data.length; i++){
23+
for (let i = 0; i < in_data.length; i++) {
2424

2525
let elem = in_data[i]
2626
let elem_index = labels.indexOf(elem)
@@ -39,104 +39,104 @@ function oneHot(in_data, prefix, prefix_sep){
3939
* columns: [Array] columns to be encoded in DataFrame.
4040
* }
4141
*/
42-
function get_dummy(kwargs={}){
43-
utils.__in_object(kwargs,"data", "data not provided")
42+
function get_dummy(kwargs = {}) {
43+
utils.__in_object(kwargs, "data", "data not provided")
4444

45-
let prefix = kwargs["prefix"] || null
46-
let prefix_sep = kwargs["prefix_sep"] || ["_"]
47-
let columns = kwargs["columns"] || null
45+
let prefix = kwargs["prefix"] || null
46+
let prefix_sep = kwargs["prefix_sep"] || ["_"]
47+
let columns = kwargs["columns"] || null
4848

49-
let is_dataframe = false
50-
let in_data = null;
49+
let is_dataframe = false
50+
let in_data = null;
5151

52-
if(Array.isArray(kwargs["data"])){
53-
in_data = kwargs["data"]
54-
}
55-
else if( kwargs["data"] instanceof DataFrame){
56-
in_data = kwargs["data"]
57-
is_dataframe = true;
58-
}
59-
else{
60-
in_data = kwargs["data"].values
52+
if (Array.isArray(kwargs["data"])) {
53+
in_data = kwargs["data"]
54+
}
55+
else if (kwargs["data"] instanceof DataFrame) {
56+
in_data = kwargs["data"]
57+
is_dataframe = true;
58+
}
59+
else {
60+
in_data = kwargs["data"].values
61+
}
62+
63+
if (!is_dataframe) {
64+
let [onehot_data, prefix_labels] = oneHot(in_data, prefix, prefix_sep)
65+
66+
return new DataFrame(onehot_data, { columns: prefix_labels })
67+
}
68+
else {
69+
70+
let column_index = []
71+
if (!columns) {
72+
columns = [];
73+
in_data.col_types.map((x, i) => {
74+
75+
if (x == "string") {
76+
let name_column = in_data.columns[i]
77+
columns.push(name_column);
78+
column_index.push(i);
79+
}
80+
});
81+
} else {
82+
83+
columns.forEach((x) => {
84+
let col_idx = columns.indexOf(x)
85+
column_index.push(col_idx);
86+
});
6187
}
6288

63-
if(!is_dataframe){
64-
let [onehot_data, prefix_labels] = oneHot(in_data, prefix, prefix_sep)
65-
66-
return new DataFrame(onehot_data,{columns: prefix_labels})
89+
if (prefix) {
90+
if (Array.isArray(prefix)) {
91+
if (prefix.length != columns.length) {
92+
throw new Error("prefix must be the same length with the number of onehot encoding column")
93+
}
94+
} else {
95+
throw new Error("prefix for dataframe must be an array")
96+
}
97+
} else {
98+
prefix = columns
6799
}
68-
else{
69-
70-
let column_index = []
71-
if(!columns){
72-
columns = [];
73-
in_data.col_types.map((x,i)=>{
74-
75-
if(x == "string"){
76-
let name_column = in_data.columns[i]
77-
columns.push(name_column);
78-
column_index.push(i);
79-
}
80-
});
81-
}else{
82100

83-
columns.forEach((x) => {
84-
let col_idx = columns.indexOf(x)
85-
column_index.push(col_idx);
101+
let df_data = in_data.values
102+
let df_columns = in_data.columns
103+
let col_data = in_data.col_data
104+
105+
let column_data = []
106+
column_index.forEach((x) => {
107+
column_data.push(col_data[x])
108+
});
109+
110+
let one_hotColumns = []
111+
let one_hotData = []
112+
column_data.forEach((data, i) => {
113+
114+
let [onehot_data, prefix_labels] = oneHot(data, prefix[i], prefix_sep)
115+
one_hotColumns.push(...prefix_labels);
116+
117+
if (one_hotData.length == 0) {
118+
one_hotData.push(...onehot_data);
119+
} else {
120+
onehot_data.forEach((x, i) => {
121+
one_hotData[i].push(...x);
86122
});
87123
}
88-
89-
if(prefix){
90-
if(Array.isArray(prefix)){
91-
if(prefix.length != columns.length ){
92-
throw new Error("prefix must be the same length with the number of onehot encoding column")
93-
}
94-
}else{
95-
throw new Error("prefix for dataframe must be an array")
96-
}
97-
}else{
98-
prefix = columns
99-
}
100124

101-
let df_data = in_data.values
102-
let df_columns = in_data.columns
103-
let col_data = in_data.col_data
125+
})
104126

105-
let column_data = []
106-
column_index.forEach((x)=>{
107-
column_data.push(col_data[x])
108-
});
127+
let final_data = df_data.map((elem, i) => {
109128

110-
let one_hotColumns = []
111-
let one_hotData = []
112-
column_data.forEach((data,i)=>{
113-
114-
let [onehot_data, prefix_labels] = oneHot(data,prefix[i],prefix_sep)
115-
one_hotColumns.push(...prefix_labels);
116-
117-
if(one_hotData.length == 0){
118-
one_hotData.push(...onehot_data);
119-
}else{
120-
onehot_data.forEach((x,i)=>{
121-
one_hotData[i].push(...x);
122-
});
123-
}
129+
let ele = elem.slice();
130+
let dt = utils.__remove_arr(ele, column_index)
131+
dt.push(...one_hotData[i])
132+
return dt
133+
});
124134

125-
})
135+
let final_columns = utils.__remove_arr(df_columns, column_index);
136+
final_columns.push(...one_hotColumns)
126137

127-
let final_data = df_data.map((elem,i)=>{
128-
129-
let ele = elem.slice();
130-
let dt = utils.__remove_arr(ele,column_index)
131-
dt.push(...one_hotData[i])
132-
return dt
133-
});
134-
135-
let final_columns = utils.__remove_arr(df_columns,column_index);
136-
final_columns.push(...one_hotColumns)
137-
138-
return new DataFrame(final_data,{columns:final_columns});
139-
}
138+
return new DataFrame(final_data, { columns: final_columns });
139+
}
140140

141141
}
142142

‎danfojs/src/preprocessing/scalers.js‎

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -92,8 +92,8 @@ export class StandardScaler {
9292
let tensor_data = null
9393
if (Array.isArray(data)) {
9494
tensor_data = tf.tensor(data)
95-
}
96-
else if ((data instanceof DataFrame) || (data instanceof Series)) {
95+
96+
}else if ((data instanceof DataFrame) || (data instanceof Series)) {
9797
if (data.dtypes.includes("string")) {
9898
throw Error("Dtype Error: Cannot perform operation on string dtypes")
9999
}
@@ -145,7 +145,6 @@ export class StandardScaler {
145145
} else {
146146
throw Error("Value Error: Data type not supoorted")
147147
}
148-
// return new DataFrame(data=output_data)
149148

150149
}
151150
}

‎package.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@
2323
"table": "^5.4.6"
2424
},
2525
"scripts": {
26-
"test": "nyc mocha --require @babel/register danfojs/tests/preprocessing/encodings",
26+
"test": "nyc mocha --require @babel/register danfojs/tests/*",
2727
"dev": "npm run lint && babel ./danfojs/src -d dist --no-comments",
2828
"build": "babel ./danfojs/src -d ./dist --no-comments",
2929
"lint": "eslint ./danfojs/src",

0 commit comments

Comments
 (0)