File size: 11,158 Bytes
d4c7aae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
import pandas as pd
import numpy as np


def generate_material_usage_cost_matrix(process_df, material_usage_df):
    overall_cost_matrix = pd.DataFrame()
    overall_amount_matrix = pd.DataFrame()
    process_df = process_df.reset_index()

    # Find Unique for fixed the column of dataframe and Matrix
    unique_material_id = material_usage_df["_id"].unique()

    for index in process_df.index:
        selected_process = process_df.iloc[index]

        # Find Unique Material
        # Find All Material Usage
        selected_process_material = material_usage_df[
            material_usage_df["process_id"] == selected_process["process_id"]
        ]
        cost_dict = {}
        amount_dict = {}

        # Iteration Over Material
        for idx in range(len(selected_process_material)):
            selected_data = selected_process_material.iloc[idx]
            material_id = selected_data["_id"]
            cost = selected_data["unit_cost"]
            amount = selected_data["amount"]
            cost_dict[material_id] = cost
            amount_dict[material_id] = amount

        # Iteration Over Rest of Material
        for material_id in unique_material_id:
            if material_id not in cost_dict:
                cost_dict[material_id] = 0
                amount_dict[material_id] = 0

        cost_df = pd.DataFrame(
            cost_dict, index=[selected_process["process_id"]])
        amount_df = pd.DataFrame(
            amount_dict, index=[selected_process["process_id"]])

        overall_cost_matrix = pd.concat([overall_cost_matrix, cost_df], axis=0)
        overall_amount_matrix = pd.concat(
            [overall_amount_matrix, amount_df], axis=0)

    # Reorder Column to be same normal and validation
    column_list = unique_material_id.tolist()
    ordered_columns = sorted(column_list)
    overall_cost_matrix = overall_cost_matrix[ordered_columns]
    overall_amount_matrix = overall_amount_matrix[ordered_columns]

    overall_cost_matrix.fillna(0, inplace=True)
    overall_amount_matrix.fillna(0, inplace=True)

    return (overall_cost_matrix, overall_amount_matrix)


def generate_employee_usage_cost_matrix(process_df, employee_usage_df):
    overall_cost_matrix = pd.DataFrame()
    overall_duration_matrix = pd.DataFrame()
    overall_day_amount_matrix = pd.DataFrame()

    employee_usage_df["duration"] = (
        employee_usage_df["duration"] * employee_usage_df["amount"]
    )

    unique_emp_id = employee_usage_df["employee_id"].unique()

    process_df = process_df.reset_index()

    # Iteration Over each process
    for index in process_df.index:
        selected_process = process_df.iloc[index]
        selected_process_employee = employee_usage_df[
            employee_usage_df["process_id"] == selected_process["process_id"]
        ]

        ec_cost_dict = {}
        ec_duration_dict = {}
        ec_day_amount_dict = {}

        unique_process_employee = selected_process_employee["employee_id"].unique(
        )
        unique_pe_df = pd.DataFrame(
            unique_process_employee, columns=["employee_id"])

        # Adust Employee
        # Converse many employee record to one record for each employee in one process
        # Process will can contain many of employee but 1 employee only 1 record
        for idx in range(len(unique_pe_df)):
            selected_data = unique_pe_df.iloc[idx]
            all_record = selected_process_employee[
                selected_process_employee["employee_id"] == selected_data["employee_id"]
            ]
            first_record = all_record.iloc[0]
            # Cost also the same pick from the first record
            cost = first_record["cost"]
            day_amount = first_record["day_amount"]
            # Duration is the sum of all duration of employee in the process
            duration = all_record["duration"].sum()
            # Update the record of unique_pe_df add cost and duration
            unique_pe_df.loc[idx, "cost"] = cost
            unique_pe_df.loc[idx, "duration"] = duration
            unique_pe_df.loc[idx, "day_amount"] = day_amount
            unique_pe_df.loc[idx, "process_id"] = first_record["process_id"]

        for idx in range(len(unique_pe_df)):
            selected_data = unique_pe_df.iloc[idx]
            cost = selected_data["cost"]
            employee_id = selected_data["employee_id"]
            duration = selected_data["duration"]
            day_amount = selected_data["day_amount"]

            ec_cost_dict[employee_id] = cost
            ec_duration_dict[employee_id] = duration
            ec_day_amount_dict[employee_id] = day_amount

        # Iteration Over Rest of Employee

        for employee_id in unique_emp_id:
            if employee_id not in ec_cost_dict:
                ec_cost_dict[employee_id] = 0
                ec_duration_dict[employee_id] = 0
                ec_day_amount_dict[employee_id] = 1

        employee_cost_df = pd.DataFrame(
            ec_cost_dict, index=[selected_process["process_id"]]
        )

        employee_duration_df = pd.DataFrame(
            ec_duration_dict, index=[selected_process["process_id"]]
        )

        employee_dayamount_df = pd.DataFrame(
            ec_day_amount_dict, index=[selected_process["process_id"]]
        )

        overall_cost_matrix = pd.concat(
            [overall_cost_matrix, employee_cost_df], axis=0
        )

        overall_duration_matrix = pd.concat(
            [overall_duration_matrix, employee_duration_df], axis=0
        )

        overall_day_amount_matrix = pd.concat(
            [overall_day_amount_matrix, employee_dayamount_df], axis=0
        )

    # Reorder Column to be same normal and validation

    # Reorder for Emploee
    column_list = unique_emp_id.tolist()
    ordered_columns = sorted(column_list)
    overall_cost_matrix = overall_cost_matrix[ordered_columns]
    overall_duration_matrix = overall_duration_matrix[ordered_columns]
    overall_day_amount_matrix = overall_day_amount_matrix[ordered_columns]

    overall_cost_matrix.fillna(0, inplace=True)
    overall_duration_matrix.fillna(0, inplace=True)
    overall_day_amount_matrix.fillna(1, inplace=True)

    return (
        overall_cost_matrix,
        overall_duration_matrix,
        overall_day_amount_matrix,
    )


def generate_capital_cost_matrix(process_df, capital_cost_df):
    cost_df = pd.DataFrame()
    day_amount_df = pd.DataFrame()
    duration_df = pd.DataFrame()
    process_df = process_df.reset_index()

    # Find Unique id to fixed the column of dataframe and Matrix
    unique_capital_cost_id = capital_cost_df["_id"].unique()

    # Iteration Over each process
    for index in process_df.index:
        selected_process = process_df.iloc[index]
        selected_process_capitalcost = capital_cost_df[
            capital_cost_df["process_id"] == selected_process["process_id"]
        ]

        cost_dict = {}
        day_amount_dict = {}
        duration_dict = {}
        uniq_process_cc = selected_process_capitalcost["_id"].unique()

        uniq_pcc_df = pd.DataFrame(
            uniq_process_cc, columns=["capital_cost_id"])

        # Adust Capital Cost
        # Converse many capital Cost record to one record for each capital Cost in one process
        # Process will can contain many of capital cost but 1 capital cost only 1 record
        for idx in range(len(uniq_pcc_df)):
            selected_data = uniq_pcc_df.iloc[idx]
            all_record = selected_process_capitalcost[
                selected_process_capitalcost["_id"] == selected_data["capital_cost_id"]
            ]
            first_record = all_record.iloc[0]
            # Cost also the same pick from the first record
            cost = first_record["cost"]
            # Duration is the sum of all duration of employee in the process
            duration = all_record["duration"].sum()
            # Update the record of unique_pe_df add cost and duration
            uniq_pcc_df.loc[idx, "cost"] = cost
            uniq_pcc_df.loc[idx, "duration"] = duration
            uniq_pcc_df.loc[idx, "day_amount"] = first_record["day_amount"]
            uniq_pcc_df.loc[idx, "process_id"] = first_record["process_id"]

        # Iteration Only for 1 cc per record data
        for idx in range(len(uniq_pcc_df)):
            selected_data = uniq_pcc_df.iloc[idx]
            cost = selected_data["cost"]
            duration = selected_data["duration"]
            captial_cost_id = selected_data["capital_cost_id"]
            cost_dict[captial_cost_id] = cost
            day_amount_dict[captial_cost_id] = selected_data["day_amount"]
            duration_dict[captial_cost_id] = duration

        # Do for the rest of capital cost object
        for cc_id in unique_capital_cost_id:
            if cc_id not in cost_dict:
                cost_dict[cc_id] = 0
                day_amount_dict[cc_id] = 1
                duration_dict[cc_id] = 0

        # Dataframe Generation
        sub_cost_df = pd.DataFrame(
            cost_dict, index=[selected_process["process_id"]])
        sub_duration_df = pd.DataFrame(
            duration_dict, index=[selected_process["process_id"]]
        )
        sub_dayamount_df = pd.DataFrame(
            day_amount_dict, index=[selected_process["process_id"]]
        )

        # Generate Matrix
        cost_df = pd.concat([cost_df, sub_cost_df], axis=0)
        day_amount_df = pd.concat([day_amount_df, sub_dayamount_df], axis=0)
        duration_df = pd.concat([duration_df, sub_duration_df], axis=0)

    # Reorder the Column to be same on Training and validation

    column_list = unique_capital_cost_id.tolist()
    sorted_column = sorted(column_list)

    day_amount_df = day_amount_df[sorted_column]
    cost_df = cost_df[sorted_column]
    duration_df = duration_df[sorted_column]

    day_amount_df.fillna(1, inplace=True)
    cost_df.fillna(0, inplace=True)
    duration_df.fillna(1, inplace=True)

    return (cost_df, day_amount_df, duration_df)


def generate_price_matrix(process_df, use_3d=False, use_unit_cost=True):
    price_arr = []
    process_df = process_df.reset_index()
    if use_unit_cost:
        for index in process_df.index:
            selected_data = process_df.iloc[index]
            cost = selected_data["cost"]
            if use_3d:
                price_arr.append([[cost]])
            else:
                price_arr.append([cost])
    else:
        for index in process_df.index:
            selected_data = process_df.iloc[index]
            if use_3d:
                price_arr.append([[selected_data["cost"]]])
            else:
                price_arr.append([selected_data["cost"]])
    price_arr = np.array(price_arr)
    return price_arr


def generate_duration_matrix(process_df, use_3d=False):
    duration_array = []
    process_df = process_df.reset_index()
    for index in process_df.index:
        selected_data = process_df.iloc[index]
        duration = selected_data["duration"]
        if use_3d:
            duration_array.append([[duration]])
        else:
            duration_array.append([duration])

    duration_array = np.array(duration_array)
    return duration_array