Spaces:
Running
Running
File size: 6,496 Bytes
43c7e13 |
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 |
from joblib import dump, load
import pandas as pd
from sklearn import metrics
from flask import flash
import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics.pairwise import cosine_similarity
from sklearn import metrics
def data_similarity(df,pt,index,column,value):
# index fetch
index = np.where(pt.index==index)[0][0]
similarity_scores = cosine_similarity(pt)
similar_items = sorted(list(enumerate(similarity_scores[index])),key=lambda x:x[1],reverse=True)[1:2]
data = []
for i in similar_items:
item = []
temp_df = df[df['index'] == pt.index[i[0]]]
item.extend(list(temp_df.drop_duplicates(index)[value].values))
#item.extend(list(temp_df.drop_duplicates(index)[column].values))
#item.extend(list(temp_df.drop_duplicates(index)[index].values))
data.append(item)
list = [item.item() if isinstance(item, np.generic) else item for sublist in data for item in sublist]
original_values = [list['Change_cts_value'].inverse_transform([val]) for val in list]
return original_values
def recommendation_generator(df):
try:
pivot_cts = df.pivot_table(index='EngCts', columns='MkblCts', values='Change_cts_value')
pivot_shp = df.pivot_table(index='EngShp', columns='MkblShp', values='change_shape_value')
pivot_qua = df.pivot_table(index='EngQua', columns='MkblQua', values='Change_quality_value')
pivot_col = df.pivot_table(index='EngCol', columns='MkblCol', values='Change_color_value')
pivot_cut = df.pivot_table(index='EngCut', columns='MkblCut', values='Change_cut_value')
#==============================================================================
# # Recommendation
#==============================================================================
cts_data = data_similarity(df,pivot_cts,'EngCts','MkblCts','Change_cts_value')
shp_data = data_similarity(df,pivot_shp,'EngShp','MkblShp','Change_shape_value')
qua_data = data_similarity(df,pivot_qua,'EngQua','MkblQua','Change_quality_value')
col_data = data_similarity(df,pivot_col,'EngCol','MkblCol','Change_color_value')
cut_data = data_similarity(df,pivot_cut,'EngCut','MkblCut','Change_cut_value')
return cts_data,shp_data,qua_data,col_data,cut_data
except Exception as e:
flash(f'Error generating recommendation: {e}', 'error')
return None
def classification_report(df):
try:
classifcation_data = df[["EngGraphCts","EngCts","EngShp","EngQua","EngCol","EngCut","EngPol","EngSym","EngFlo","EngNts","EngMikly","EngLab","EngAmt",
"MkblCts","MkblShp","MkblQua","MkblCol","MkblCut","MkblPol","MkblSym","MkblFlo","MkblNts","MkblMikly","MkblLab","MkblAmt"]]
#==============================================================================
# # Feature Engineering to generate new columns
#==============================================================================
# Make predictions
classifcation_data["Cts_diff_eng_mkbl"] = round(classifcation_data["EngCts"] - classifcation_data["MkblCts"],2)
# Create a new column 'Change_Label' based on the values in 'Cts_diff_eng_mkbl'
classifcation_data['Change_cts_value'] = classifcation_data['Cts_diff_eng_mkbl'].apply(
lambda x: str(x)+' negative change' if x < 0 else (str(x)+' positive change' if x > 0 else 'no change')
)
# Create a new column 'Shape_Change' based on the values in 'EngShp' and 'MkblShp'
classifcation_data['Change_shape_value'] = classifcation_data.apply(
lambda row: str(row['EngShp'])+' to '+str(row['MkblShp'])+' shape change' if row['EngShp'] != row['MkblShp'] else 'shape not change', axis=1
)
# Create a new column 'quality_Change' based on the values in 'EngQua' and 'MkblQua'
classifcation_data['Change_quality_value'] = classifcation_data.apply(
lambda row: str(row['EngQua'])+' to '+str(row['MkblQua'])+' quality change' if row['EngQua'] != row['MkblQua'] else 'quality not change', axis=1
)
# Create a new column 'color_Change' based on the values in 'EngCol' and 'MkblCol'
classifcation_data['Change_color_value'] = classifcation_data.apply(
lambda row: str(row['EngCol'])+' to '+str(row['MkblCol'])+' color change' if row['EngCol'] != row['MkblCol'] else 'color not change', axis=1
)
# Create a new column 'cut_Change' based on the values in 'EngCut' and 'MkblCut'
classifcation_data['Change_cut_value'] = classifcation_data.apply(
lambda row: str(row['EngCut'])+' to '+str(row['MkblCut'])+' cut change' if row['EngCut'] != row['MkblCut'] else 'cut not change', axis=1
)
#==============================================================================
# # Label Encoding and storing the label encoders
#==============================================================================
# Get list of categorical variables
s = (classifcation_data.dtypes =="object")
object_cols = list(s[s].index)
print("Categorical variables:")
print(object_cols)
# Make copy to avoid changing original data
label_data = classifcation_data.copy()
# Apply label encoder to each column with categorical data
label_encoder = LabelEncoder()
for col in object_cols:
label_data[col] = label_encoder.fit_transform(label_data[col])
dump(label_encoder, f"./AI_In_Diamond_Industry/Label_encoders/label_encoder_{col}.joblib")
label_data.head()
#==============================================================================
# # recommendation_system
#==============================================================================
df=classifcation_data.copy()
=recommendation_generator(df)
return label_data
except Exception as e:
flash(f'Error generating classification report: {e}', 'error')
return None
|