-
Notifications
You must be signed in to change notification settings - Fork 0
/
app.py
147 lines (113 loc) · 4.55 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
import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
matplotlib.use('Agg')
import seaborn as sns
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.tree import DecisionTreeClassifier
def main():
st.title('Visualizer')
st.text('Built with Streamlit')
activities = ["EDA","Plot","Model Building","About"]
choice = st.sidebar.selectbox("Select Activity",activities)
if choice == 'EDA' :
st.subheader("Exploratory Data Analysis!!")
data = st.file_uploader("Upload Dataset",type = ["csv","txt","xls"])
if data is not None:
df = pd.read_csv(data)
st.dataframe(df.head())
if st.checkbox("Show shape"):
st.write(df.shape)
if st.checkbox("Show Columns"):
all_columns = df.columns.to_list()
st.write(all_columns)
if st.checkbox("Select Columns To Show"):
selected_columns = st.multiselect("Select Columns",all_columns)
new_df = df[selected_columns]
st.dataframe(new_df)
if st.checkbox("Show Summary"):
st.write(df.describe())
if st.checkbox("Show Value Counts"):
st.write(df.iloc[:,-1].value_counts()) # select the target columns..assuming last columns is target columns
elif choice == 'Plot' :
st.subheader("Data Visualization")
data = st.file_uploader("Upload Dataset",type = ["csv","txt","xls"])
if data is not None:
df = pd.read_csv(data)
st.dataframe(df.head())
if st.checkbox("Correlation with Seaborn"):
st.write(sns.heatmap(df.corr(),annot = True))
st.pyplot()
if st.checkbox("Pie chart"):
all_columns = df.columns.to_list()
columns_to_plot = st.selectbox("Select Column",all_columns)
pie_plot = df[columns_to_plot].value_counts().plot.pie(autopct = "%1.1f%%")
st.write(pie_plot)
st.pyplot()
all_columns_names = df.columns.to_list()
type_of_plot = st.selectbox("Select type of Plot",["area","bar","line","hist","box","kde"])
selected_columns_names = st.multiselect("Select Columns To Plot",all_columns_names)
if st.button("Generate Plot"):
st.success("Generating Customizable Plot {} for {}".format(type_of_plot,selected_columns_names))
if type_of_plot == 'area':
collect_data = df[selected_columns_names]
st.area_chart(collect_data)
elif type_of_plot == 'bar':
collect_data = df[selected_columns_names]
st.bar_chart(collect_data)
elif type_of_plot == 'line':
collect_data = df[selected_columns_names]
st.line_chart(collect_data)
elif type_of_plot:
collect_data = df[selected_columns_names].plot(kind = type_of_plot)
st.write(collect_data)
st.pyplot()
elif choice == 'Model Building' :
st.subheader("Building ML Model")
data = st.file_uploader("Upload Dataset",type = ["csv","txt","xls"])
if data is not None:
df = pd.read_csv(data)
st.dataframe(df.head())
X = df.iloc[:,0:-1]
Y = df.iloc[:,-1]
seed = 7
# Model Building : Assuming last column is target columns
models = []
models.append(("LR",LogisticRegression()))
models.append(("LDA",LinearDiscriminantAnalysis()))
models.append(("KNN",KNeighborsClassifier()))
models.append(("CART",DecisionTreeClassifier()))
models.append(("NB",GaussianNB()))
models.append(("SVM",SVC()))
# Evaluate each model in turn
model_names = []
model_mean = []
model_std = []
all_models = []
scoring = 'accuracy'
for name,model in models:
kfold = model_selection.KFold(n_splits=10,random_state=seed)
cv_results = model_selection.cross_val_score(model,X,Y,cv = kfold,scoring=scoring)
model_names.append(name)
model_mean.append(cv_results.mean())
model_std.append(cv_results.std())
accuracy_results = {"model_name":name,"model_accuracy":cv_results.mean(),"standard_deviation":cv_results.std()}
all_models.append(accuracy_results)
if st.checkbox("Metrics as Table"):
st.dataframe(pd.DataFrame(zip(model_names,model_mean,model_std),columns = ["Model","Accuracy","Standard_Deviation"]))
if st.checkbox("Metrics as JSON"):
st.json(all_models)
elif choice == 'About' :
st.subheader("About")
st.markdown("""This project focuses at providing a more comprehensive way to interact with data.Created an Data
Visualization App using Streamlit library which works well with any data and help to Visualize
and extract relevant information from data in more easier way""")
if __name__ == '__main__':
main()