-
Notifications
You must be signed in to change notification settings - Fork 0
/
app.py
170 lines (145 loc) · 5.54 KB
/
app.py
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
from flask import Flask, render_template, request, jsonify
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
import seaborn as sns
from scipy import stats
from sklearn.metrics import mean_squared_error
app = Flask(__name__)
app.secret_key = "mysecretkey"
@app.route("/")
def home():
return render_template("index.html")
@app.route("/upload", methods=["POST"])
def upload():
if request.method == "POST":
file = request.files["file"]
global df
df = pd.read_csv(file)
# Replace '?' and '' with NaN
df.replace("?", np.NaN, inplace=True)
df.replace("", np.NaN, inplace=True)
# Delete Rows that contain duplicates
df.drop_duplicates(inplace=True)
# Delete Columns that have single values
for key, value in df.items():
if len(df[key].unique()) == 1:
del df[key]
miss_data = df.isnull().sum()[df.isnull().sum() > 0]
miss_data = miss_data.to_frame()
miss_data.columns = ["No of Missing Values"]
cols = list(miss_data.index)
dataType = df.dtypes
dataType = dataType.to_frame()
# return jsonify(
# {
# "data": df.to_json(),
# # "dataType": dataType.transpose().to_json(),
# "cols": cols,
# "columns": list(df.columns),
# }
# )
return render_template(
"advance_cleaning.html",
data=df,
dataType=dataType.transpose(),
cols=cols,
columns=list(df.columns),
)
@app.route("/advance_cleaning", methods=["GET", "POST"])
def advance_cleaning():
global df
clean_message = None
if request.method == "POST":
if request.form["action"] == "replace_missing":
columns = request.form.getlist("replace_column")
method = request.form["replace_method"]
for col in columns:
if method == "mean":
avg = df[col].astype("float").mean(axis=0)
df[col].replace(np.NaN, avg, inplace=True)
elif method == "freq":
freq = df[col].value_counts().idxmax()
df[col].replace(np.NaN, freq, inplace=True)
elif method == "deleteRow":
df.dropna(subset=[columns[0]], axis=0, inplace=True)
df.reset_index(drop=True, inplace=True)
clean_message = "Missing values replaced successfully!"
elif request.form["action"] == "change_datatype":
column = request.form.getlist("column")
datatype = request.form["datatype"]
for col in column:
df[col] = df[col].astype(datatype)
clean_message = "Data type changed successfully!"
elif request.form["action"] == "normalize_data":
cols = request.form.getlist("column")
for col in cols:
df[col] = df[col] / df[col].max()
clean_message = "Data normalized successfully!"
# elif request.form["action"] == "convert_categorical":
# columns = request.form.getlist("columns")
# dummyframe = pd.get_dummies(df, columns=columns, prefix=columns)
# # dummyframe2 = pd.get_dummies(df['aspiration'])
# # dummyframe2.rename(columns={'std':'aspiration-std','turbo':'aspiration-turbo'}, inplace=True)
# # merge the dummyframe2 to main data frame and remove th aspiration column
# df = pd.concat([df, dummyframe], axis=1)
# # df.drop('aspiration', axis=1, inplace=True)
# clean_message = "Categorical data converted to integer successfully!"
miss_data = df.isnull().sum()[df.isnull().sum() > 0]
miss_data = miss_data.to_frame()
miss_data.columns = ["No of Missing Values"]
cols = list(miss_data.index)
dataType = df.dtypes
dataType = dataType.to_frame()
return render_template(
"advance_cleaning.html",
data=df,
dataType=dataType.transpose(),
cols=cols,
columns=list(df.columns),
clean_message=clean_message,
)
@app.route("/visualization", methods=["GET", "POST"])
def visualization():
return render_template("visualize.html")
@app.route("/analysis", methods=["GET", "POST"])
def analysis():
global df
dict = {}
if request.method == "POST":
if request.form["action"] == "check_correlation":
col = request.form.get("target_column")
print(type(col))
for key, val in df.items():
type(key)
if key == col:
break
pearson_coef, p_value = stats.pearsonr(df[key], df[col])
dict[key] = p_value
elif request.form["action"] == "SLR":
lm = LinearRegression()
columns = request.form.getlist("columnX")
col = request.form.get("target_column")
X = df[columns]
Y = df[col]
lm.fit(X, Y)
R2 = lm.score(X, Y)
MSE = mean_squared_error(df[col], Yhat)
Yhat = lm.predict(X)
Yhat[0:5]
width = 12
height = 10
plt.figure(figsize=(width, height))
sns.regplot(x=columns, y=col, data=df)
plt.ylim(
0,
)
plt.show()
return render_template(
"analysis.html",
data=df,
cols=list(df.columns),
)
if __name__ == "__main__":
app.run(debug=True)